In this study, we constructed the credit-scoring model of P2P loans by using several machine learning and artificial neural network (ANN) methods, including logistic regression (LR), a support vector machine, a decision tree, random forest, XGBoost, LightGBM and 2-layer neural networks. This study explores several hyperparameter settings for each method by performing a grid search and cross-validation to get the most suitable credit-scoring model in terms of training time and test performance. In this study, we get and clean the open P2P loan data from Lending Club with feature engineering concepts. In order to find significant default factors, we used an XGBoost method to pre-train all data and get the feature importance. The 16 selected features can provide economic implications for research about default prediction in P2P loans. Besides, the empirical result shows that gradient-boosting decision tree methods, including XGBoost and LightGBM, outperform ANN and LR methods, which are commonly used for traditional credit scoring. Among all of the methods, XGBoost performed the best.
Citation: An-Hsing Chang, Li-Kai Yang, Rua-Huan Tsaih, Shih-Kuei Lin. Machine learning and artificial neural networks to construct P2P lending credit-scoring model: A case using Lending Club data[J]. Quantitative Finance and Economics, 2022, 6(2): 303-325. doi: 10.3934/QFE.2022013
| [1] | M. Kanta Rao, Ch. N. Satish Kumar . Influence of fly ash on hydration compounds of high-volume fly ash concrete. AIMS Materials Science, 2021, 8(2): 301-320. doi: 10.3934/matersci.2021020 |
| [2] | Reginald Umunakwe, Ifeoma Janefrances Umunakwe, Uzoma Samuel Nwigwe, Wilson Uzochukwu Eze, Akinlabi Oyetunji . Review on properties of hybrid aluminum–ceramics/fly ash composites. AIMS Materials Science, 2020, 7(6): 859-870. doi: 10.3934/matersci.2020.6.859 |
| [3] | Grzegorz Ludwik Golewski . Mechanical properties and brittleness of concrete made by combined fly ash, silica fume and nanosilica with ordinary Portland cement. AIMS Materials Science, 2023, 10(3): 390-404. doi: 10.3934/matersci.2023021 |
| [4] | Stelladriana Volpe, Andrea Petrella, Valentino Sangiorgio, Michele Notarnicola, Francesco Fiorito . Preparation and characterization of novel environmentally sustainable mortars based on magnesium potassium phosphate cement for additive manufacturing. AIMS Materials Science, 2021, 8(4): 640-658. doi: 10.3934/matersci.2021039 |
| [5] | Ketut Aswatama Wiswamitra, Sri Murni Dewi, Moch. Agus Choiron, Ari Wibowo . Heat resistance of lightweight concrete with plastic aggregate from PET (polyethylene terephthalate)-mineral filler. AIMS Materials Science, 2021, 8(1): 99-118. doi: 10.3934/matersci.2021007 |
| [6] | Kong Fah Tee, Sayedali Mostofizadeh . Numerical and experimental investigation of concrete with various dosages of fly ash. AIMS Materials Science, 2021, 8(4): 587-607. doi: 10.3934/matersci.2021036 |
| [7] | Hashem Al-Mattarneh, Musab Abuaddous, Rabah Ismail, Ahmad B. Malkawi, Yaser Jaradat, Hamsa Nimer, Mohanad Khodier . Performance of concrete paving materials incorporating biomass olive oil waste ash and nano-silica. AIMS Materials Science, 2024, 11(5): 1035-1055. doi: 10.3934/matersci.2024049 |
| [8] | Olatunji P Abolusoro, Moshibudi Caroline Khoathane, Washington Washington . Mechanical and microstructural characteristics of recycled aluminium matrix reinforced with rice husk ash. AIMS Materials Science, 2024, 11(5): 918-934. doi: 10.3934/matersci.2024044 |
| [9] | Wisawat Keaswejjareansuk, Xiang Wang, Richard D. Sisson, Jianyu Liang . Electrospinning process control for fiber-structured poly(Bisphenol A-co-Epichlorohydrin) membrane. AIMS Materials Science, 2020, 7(2): 130-143. doi: 10.3934/matersci.2020.2.130 |
| [10] | Filipe Figueiredo, Pamela da Silva, Eriton R. Botero, Lino Maia . Concrete with partial replacement of natural aggregate by PET aggregate—An exploratory study about the influence in the compressive strength. AIMS Materials Science, 2022, 9(2): 172-183. doi: 10.3934/matersci.2022011 |
In this study, we constructed the credit-scoring model of P2P loans by using several machine learning and artificial neural network (ANN) methods, including logistic regression (LR), a support vector machine, a decision tree, random forest, XGBoost, LightGBM and 2-layer neural networks. This study explores several hyperparameter settings for each method by performing a grid search and cross-validation to get the most suitable credit-scoring model in terms of training time and test performance. In this study, we get and clean the open P2P loan data from Lending Club with feature engineering concepts. In order to find significant default factors, we used an XGBoost method to pre-train all data and get the feature importance. The 16 selected features can provide economic implications for research about default prediction in P2P loans. Besides, the empirical result shows that gradient-boosting decision tree methods, including XGBoost and LightGBM, outperform ANN and LR methods, which are commonly used for traditional credit scoring. Among all of the methods, XGBoost performed the best.
Concrete is the single most widely used material on earth after water [1,2]. Concrete is the mixture of naturally occurring agammaegate of about 70-80% followed by fillers and binding materials such as cement [3]. To understand the urgency of the research, the extensive utilization of concrete itself is massively destructive to human health on the plant. Concrete is one of the leading cause factors for increasing carbon footprint on earth [4]. Growing concern over the utilization of waste materials may enhance the concrete properties by replacing with cement/filler or with coarse agammaegate been trending from past decades [5]. Among the waste materials FA use has positive impact on the economic aspect as it reduces the cost of concrete production by reducing the content of expensive cement in its composition. FA use in concrete reduces industrial waste landfills followed by reduction of CO2 and green gas emission from the cement production [6]. Cenosphere addition to the concrete is to reuse waste materials which have the inverse effect on the climate change. The high demand and utilization of natural materials may cause scarcity thus preparing alternative materials would be helpful. Numerous studies have been conducted to meet with the challenge of findings alternative materials. This study is mainly focusing on the energy part. Global leaders and United Nations organizations passionately looking onto the matter of climate change. United Nations general assembly meeting 2019 largely focused on the sustainable development and green buildings to enhance the people living life in contrast to combat climate change [7,8]. The one attempt to combat with climate change is the energy conversation. Globally, building infrastructure contribute about 30% greenhouse gas emissions [9,10]. Today building infrastructure plays multiple role and people are spending much of time indoor where energy conversations and thermal comfort is important.
Dynamically, thermal comfort and energy required for the cooling and heating of the building is highly depend on the thermo-physical properties of the construction materials used in the building [11]. Concrete is the key building material and extensively use up to 10 billion tons per year and expected to increase up to 18 billion tons in 2050 [12]. The high demand and on large scale utilization has created interest among researchers to investigate thermo-physical properties of the concrete. The main thermo physical properties of the materials are thermal conductivity, specific heat and thermal diffusivity. Thermal conductivity is important because it allow the heat transfer in the material or concrete. Low heat transfer and energy consumption has been observed in the buildings constructed with lower conductive materials [13]. Conventional concrete which is most widely used in the construction is poor insulating materials with high thermal mass. Conventional concrete store heat energy absorb due to high thermal conductivity and less insulation. Study [14] postulated that light weight concrete applied in the buildings of European countries may has reduce about 15% heating energy compared to buildings constructed with normal concrete. Study [15] has modified concrete by replacing cement with FA resulted potentially high environmental benefits such as reduction of energy use for cement production. Addition of 20-30% siliceous FA to the fresh concrete significantly reduce the fracture toughness of concrete while over 28 d of cured concrete with 20% slightly increase mode KIIIc fracture followed with 30% addition of FA reduced significantly fracture toughness [16].
Thus, it is essential to find alternative lightweight materials to enhance the thermal insulation properties of concrete to reduce heat energy in the building further leads to the energy saving buildings to cope climate change global issue.
In the introduction part enlighten importance of concrete utilization in the civil engineering practice worldwide and future demand has discussed. Due to high demand and very friendly adoption nature of concrete today science engineering is focusing on the importance aspect of heat island largely generated by the concrete massive structure and impact on the climate change which cannot be ignored. Thus, the engineers and scientist are contributing to design concrete with less thermal conductivity by addition of waste materials is to cope with climate change challenge. In this review, the aim of this paper is to evaluate the techniques that can be used and also by considering the factors that affect the thermal conductivity (K-values). Thermal conductivity of concrete is seen as the important factor to monitor the heat transfer through conduction. Thermal conductivity decreases by utilization of insulating materials [13]. Generally, steady state and transient method is use to determine the thermal conductivity of the material technically both has different approach where in the steady state method temperature is constantly applied and not dependent on time. Steady state commonly chooses if the materials are homogenous.
Whereby transient method heat flow/temperature changes over time can say transient method is time dependent method. Transient method used for non-homogenous (heterogeneous) materials with moister content [13,17,18]. Study of [13] comprehensively analyzed the thermal conductivity of concrete and concluded transient method is commonly used to find the K values of concrete time, equipment availability and cost might be the reason but since concrete is not homogenous material and has always moisture content is most justified reason transient method used to find K values.
Thermal conductivity of concrete and governing factors concluded by [18] are types of agammaegate materials, cement content, water content and air voids content additionally temperature and moister condition of the concrete. Moisture content and mineralogical characteristic of concrete are leading factors of high thermal conductivity [19]. Study of [20] added light weight material such as perlite in the concrete result shows significant reduction of thermal conductivity of concrete to 0.1472 w/mK. In the concrete higher is the cement content higher is the thermal conductivity addition of powder materials like FA, steel slag help to reduce the K value because reducing the cement content. Study shows significant reduction of thermal conductivity of concrete by addition of FA [21]. Study conducted by [22] found that addition of lightweight perlite agammaegate help to reduce density, flexural strength and thermal conductivity at 70% addition is 6.3 times less than control/normal concrete. Research Study conducted by [23] has strongly recommended the low water/binder ratio for concrete mix. Moreover, high degree of homogeneity in the concrete mixes leading better performance small internal microcracks and greater resistance to dynamic loads. Expended polystyrene (EPS) was added into the concrete result indicated increasing volume of EPS significantly reduce the thermal conductivity of the concrete [24]. Natural agammaegate was replaced with modified expended polystyrene (MEPS) findings indicated that increasing the replacement of natural agammaegate with MEPS significantly reduce the thermal conductivity of the concrete [25]. Concreter incorporation with FA 30% to over 40% remarkably improves the strength properties of concrete. Cement replacement with FA in the concrete mix has significantly environmental benefits as well reduce the electricity consumed while cement productions [15]. Light weight concrete added 30% FA decreased water absorption, density, compressive strength and thermal conductivity of concrete [26]. Study claimed light foamed concrete (LFC) is highly thermal resistance compare to ordinary concrete and produce better energy efficacy for use as non-structural alternative materials in tropical climates [27]. Thermal insulation materials play an important role in reducing power requirements and greenhouse gas emissions. There are some factors mainly affecting the thermal conductivity of the concrete are types of agammaegate materials, cement, fine agammaegate, water cement ratio and moister content. Where it found that light weight concrete has the lower thermal conductivity compare to the normal concrete. Many attempts have been made in the past to reduce the thermal conductivity of concrete by adding and replacing main agammaegate materials. In this study, by products of the fly ash known cenespher is suggested to use. Cenosphere by product of the fly ash can be separated from FA using sink float method. Cenosphere possess good mechanical properties such as high compressive strength and a good thermal insulator. Conventional cement can be used with cenosphere to produce a lightweight concrete.
Table 1 shows the ordinary Portland cement (OPC) chemical composition and physical properties and type-1 cement with density of 3150 g/cm3 in accordance to ASTM C150 is used in this study.
| Chemical property | Percentage (%) | Physical property | Results |
| CaO | 60.7 | Size | ≤75 µ |
| SiO2 | 21.9 | Fineness | 91% |
| Al2O3 | 7.4 | Normal consistency | 26% |
| Fe2O3 | 5.7 | Initial stetting time | 33 min |
| MgO | 4.5 | Final stetting time | 408 min |
| SO3 | 3.9 | Specific surface | 322 m2/kg |
| K2O | 2.4 | Soundness | 1.30% |
| Na2O | 0.2 | 28-days compressive strength | 42 MPa |
DownLoad:
CSV
Natural sand was used as a FA (fine agammaegate) in all the mixes in SSD (saturated surface dry) condition. Normal weight coarse agammaegate (crush stone) in saturated dry condition (SSD), Nominal maximum size of coarse agammaegate is 19.5 mm. Different tests were performed on agammaegate to evaluate its physical property as shown in Table 2.
| Physical property | Fine aggregate | Coarse aggregate |
| Particle size (mm) | 4.75-0.075 | 19.5-4.75 |
| Fineness modulus | 2.83 | 4.3 |
| Absorption capacity (%) | 5.08 | 3.13 |
| Moisture content (%) | 2.8 | 1.25 |
| Bulk density (kg/m3) | 1586 | 1565 |
DownLoad:
CSV
Sand (Silica) is substituted by weight 10%, 20% and 30% with cenosphere. Polypropylene fiber 0.5% was added by weight to increase the workability of the concrete. Lightweight expended clay agammaegate (LECA) 2-4 mm diameter with density of 448 kg/m3 was used in this study. Compressive and tensile strength test and thermal conductivity test were conducted. All tests were carried out by following British (BS) and Malaysian JKR (Public Works Department) standards. Concrete specimens were prepared in the civil Engineering laboratory at Universiti Tenaga Nasional (Uniten) Engineering campus Malaysia. Workability of the concrete mixed is increased and maintained using superplasticer doze where polypropylene is added to increase the durability of the concrete. Table 3 shows the concrete mix design
| Control sample (0%) | Cenesphere (10%) | Cenesphere (20%) | Cenosphere (30%) | |
| Ingredients (kg) | 3.06 | 6.12 | 9.18 | |
| Cement (kg) | 15.80 | 15.80 | 15.80 | 15.80 |
| Sand (kg) | 30.60 | 27.54 | 24.48 | 21.42 |
| LECA (kg) | 25.4 | 25.4 | 25.4 | 25.4 |
| Water | 7.9 | 7.9 | 7.9 | 7.9 |
| Polypropylene fiber | 0.079 | 0.079 | 0.079 | 0.079 |
DownLoad:
CSV
The test aim is to measure the performance of concrete. Concrete cube size of 0.1 m3 was prepared and cured for 3, 7 and 28 d before tested using universal compressive testing machine.
Concrete has the lower tensile strength compare to compressive strength. Tensile test was conducted and specimen prepared size of 0.075 × 0.030 m cylinder has prepared and cured for 28 d. Universal tensile machine is used to test the tensile straight of the concrete beam.
Thermal conductivity is a test to measure the rate and amount of heat that passes through the concrete specimen in a period of time. The set point temperature will be set to 0-60 ºC in order to produce different set of results to be analyzed. Heat Flow meter FOX-50 instrument is used to measure the heat flow/thermal conductivity of the concrete samples sample casted according to the specification and tested for an hour. Specimen preparation for the thermal conductivity analysis is shown in the Figures 1-3. The 28 d cured concrete samples is shown in Figure 1.
Concrete cube dimension of 0.1 m × 0.1 m × 0.1 m with curing periods of 3, 7 & 28 d were tested for the compressive strength (MPa) in compression by using ELE International Compression Machine. Table 4 indicated the compressive strength of 3 d curing period as shown. Each specimen test has repeated three time's findings shows addition of 20% cenosphere has the highest compressive strength of 23.9 MPa. Moreover, above 30% addition reduce the compressive strength of concrete.
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 3 | Control | 1 | 4.4 |
| 2 | 5.0 | ||
| 3 | 5.1 | ||
| 10% CE | 1 | 6.1 | |
| 2 | 7.4 | ||
| 3 | 5.8 | ||
| 20% CE | 1 | 10.6 | |
| 2 | 16.9 | ||
| 3 | 23.9 | ||
| 30% CE | 1 | 11.6 | |
| 2 | 14.2 | ||
| 3 | 5.3 |
DownLoad:
CSV
Cenosphere were added 10%, 20% and 30% with the partially replacement of sand. On the 7th days curing period specimen were tested for compressive test. Findings drafted in the Table 5 shows that 20% replacement has the highest compressive strength of concrete on the 7th days of curing period. Conversely more addition of cenosphere resulted lower compressive strength of concrete.
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 7 | Control | 1 | 8.7 |
| 2 | 9.9 | ||
| 3 | 10.6 | ||
| 10% CE | 1 | 14.6 | |
| 2 | 19.8 | ||
| 3 | 18.3 | ||
| 20% CE | 1 | 20.4 | |
| 2 | 25.4 | ||
| 3 | 18.2 | ||
| 30% CE | 1 | 11.7 | |
| 2 | 12.2 | ||
| 3 | 14.3 |
DownLoad:
CSV
Modified concrete specimen was tested for compressive strength on 3rd, 7th and 28th days of curing. Table 6 shows 28th days' compressive strength result. In the comprassion result with 3rd day, 7th day and 28 d shows that compressive strength of concrete increased by addition of cenosphere 20%. More than 20% addition such as 30% addition shows lower compressive strength for 3rd day, 7th day and 28 d likewise. Study has observed that cenosphere addition up to 20% in the concrete increase the compressive strength of concrete in the range of 25-30 MPa. Highest compressive strength that has observed on 28th days is 28.8 MPa. Addition of cenesphere by 20% significantly improved the compressive strength for 3-7 and 28 d where more addition or replacement with sand shows lower compressive strength. For concrete curing day 7 with 10% CE, 30% increase of strength is achieved whereas for 20% CE, 35% increase in strength is achieved. 28 d of concrete curing is known as the day concrete reaches highest strength. Highest strength is achieved in the project with an increase of strength of 40% in 10% CE and 43% in 20% CE. Overall study found that addition of cenesphere in concrete increased the compressive strength by 43% in the curing period of 28 d.
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 28 | Control | 1 | 11.6 |
| 2 | 14.2 | ||
| 3 | 5.3 | ||
| 10% CE | 1 | 28.8 | |
| 2 | 27.3 | ||
| 3 | 24.5 | ||
| 20% CE | 1 | 28.8 | |
| 2 | 25.5 | ||
| 3 | 27.0 | ||
| 30% CE | 1 | 21.9 | |
| 2 | 17.7 | ||
| 3 | 18.5 |
DownLoad:
CSV
Split Tensile is done to observe the tensile strength of the concrete which is by splitting the cylinder at the center of the concrete. Concrete with 28 d of curing is used to obtain the highest tensile strength. The machine used for this test is Universal Testing Machine (UTM). The cylinder is placed in horizontal and two bearing plates are placed in between of the cylindrical concrete and the loads are applied gradually. The max load applied on the samples is used to calculate splitting strength. Figures 4 to 7 as shown below indicated the result of tensile strength.
Each Specimen is tested three times and average result is signified in Table 7. The average tensile strength result for the control mix is 1.131 MPa. Addition of 10% cenesphere result shows the maximum tensile strength of 2.180 MPa. Further addition of cenesphere of 20% and 30% average results shows 1.732 MPa and 1.250 MPa. The tensile strength can be seen to be increasing by addition of 10% when sand is replaced by 10% of cenesphere. This is to show that CE addition to the mix should be kept at 10% for it to work as a resistance to tensile forces. From the results, it shows that once sand is replaced by 20-30% of CE, reduction in tensile strength will happen. Highest tensile strength obtained is 2.321 MPa in design.
| Mix design | Sample No. | Splitting strength (MPa) | Average strength (MPa) |
| 0% CE | 1 | 1.003 | 1.131 |
| 2 | 1.274 | ||
| 3 | 1.117 | ||
| 10% CE | 1 | 2.321 | 2.180 |
| 2 | 2.187 | ||
| 3 | 2.033 | ||
| 20% CE | 1 | 1.649 | 1.732 |
| 2 | 2.011 | ||
| 3 | 1.535 | ||
| 30% CE | 1 | 1.341 | 1.250 |
| 2 | 1.357 | ||
| 3 | 1.051 |
DownLoad:
CSV
Thermal conductivity test is conducted using FOX 50 heat flow meter (instrument). Heat flow instrument draft the result of concrete specimen thermal conductivity, density and weight loss of the concrete sample during the process of heat flow before and after as measured. Correction factor is applied for thermal conductivity (W/mK) values because of the rubbers used in between of the samples when conducting the test in FOX 50. Two samples from each concrete mix design of 28 curing days are taken for the test. All samples were kept in the oven for 24 h to ensure moisture content completely dry. Temperature is set at 28 ºC (Malaysia temperature). Table 8 shows the thermal conductivity of concrete samples.
| Design mix | Average TC (W/mK) | Average density (kg/m3) |
| Control sample | 1.2873 | 1896.5 |
| 10% cenosphere | 1.0795 | 1895.0 |
| 20% cenosphere | 0.9463 | 1827 |
| 30% cenosphere | 0.8445 | 1592.9 |
DownLoad:
CSV
Thermal conductivity results obtained for two samples from each mix design are tabulated in Table 6. Thermal conductivity of the concrete values according to the literature shows in the range 1.0-2.5 W/mK. The result shown in the Table 6 indicated that control sample has the highest thermal conductivity of an average 1.2873 W/mK.
Density of the lightweight concrete is 1840 kg/m3. Replacement of sand 10% over cenosphere shows almost 13% reduction of thermal conductivity average values 0.9988 W/mK. Replacement of cenosphere by 20% reduces average thermal conductivity 0.9463 W/mK which is about 27% reduction in the thermal conductivity. Findings shown in the Table 6 indicated that replacement of cenosphere with sand by 30% reduce thermal conductivity of 0.8445 W/mK which is about 35%. Water cement ratio plays an important role and strict control has been taken care for every mix.
Study of [28] found that FA incorporation with concrete effectively reduce thermal conductivity and density of the concrete. Coarse agammaegates selection can play vital role in further reducing the thermal conductivity values. This can be seen in the review paper by [13] has stated the factors affecting thermal conductivity are humidity, temperature, type of agammaegate and cementing materials. Inhomogeneity and the geometry of the materials affect the thermal conductivity of the concrete mix [29]. In addition, partial evaporation of the mix design water content decreases the thermal conductivity. Cenosphere has less density compare to the water findings shown in the Table 6 indicated that density of the concrete samples decrease as the replacement of the cenosphere over sand increased. Thermal conductivity has direct relation with the density of the concrete. Thermal conductivity increased as the density increased but study witnessed replacement of sand with FA cenosphere decreased the density and positively decrease the thermal conductivity of the concrete. Higher density concrete has the higher thermal conductivity and thermal conductivity of concrete varies with the density of concrete [30]. The mineralogical character of the agammaegate greatly affects the conductivity of concrete.
Study has follow conclusions:
(1) Partial replacement of sand with cenosphere significantly increases the compressive strength of the lightweight concrete.
(2) Addition of cenosphere by 20% has significantly improved the compressive strength for 3-7 and 28 d where more addition or replacement with sand shows lower compressive strength.
(3) Compressive strength increased 40% and 43% by addition of 10% and 20% cenosphere respectively. Highest compressive strength that can be produced by the concrete is 28.8 MPa which is good for a lightweight concrete.
(4) Study concluded that tensile strength of concrete improved by replacement 10% of sand over FA cenosphere. Further addition of cenosphere shows lower tensile strength compare to 10% addition. It can conclude if desired high tensile strength in the concrete the replacement ratio keep 10% but if purpose is to achieve high compressive strength 30% addition shows the highest compressive strength of the concrete.
(5) To analyze and reduce thermal conductivity of the lightweight concrete is the main focus of this study. Study concluded that replacement of the sand with fly ash cenosphere reduces the thermal conductivity and the density of the lightweight concrete as the finding is shown in Table 5.
(6) Replacement sand over FA by 30% significantly reduces the thermal conductivity about 35%. The thermal conductivity of the control mix concrete is 1.28 W/mK where addition of 10% to 30% the thermal conductivity is reduce respectively 0.9988 W/mK, 0.9463 W/mK and 0.8445 W/mK which marked about 35% thermal conductivity has reduced.
(7) Findings indicated that cenosphere reduce the density of concrete which is the leading factor to reduce the thermal conductivity of the concrete.
(8) Study found the density of concrete has direct relation with thermal conductivity.
(9) Replacement of sand over cenosphere significantly reduces the density and thermal conductivity of the concrete.
(10) Thermal comfort in the concrete structures and copping with the climate change can be significantly reduced by the utilization of cenosphere in the concrete to replace sand. Fly ash cenosphere can be recommended to utilize in the construction projects where desired compressive strength is required this will help to reduce thermal conductivity of the concrete structures.
The authors are thankful to Universiti Tenaga Nasional Malaysia (UNITEN) for providing financial supports under BOLD 2020 (Project No: RJO10517844/041 and RJO10517844/050) for this research study.
The authors have no conflict of interest to declare.
| [1] | Aldrich JH, Nelson FD (1984) Quantitative Applications in the Social Sciences: Linear Probability, Logit, and Probit Models, Thousand Oaks, CA: SAGE Publications. https://doi.org/10.4135/9781412984744 |
| [2] | Alexander VE, Clifford CC (1996) Categorical Variables in Developmental Research: Methods of Analysis, Elsevier. https://doi.org/10.1016/B978-012724965-0/50003-1 |
| [3] |
Arya S, Eckel C, Wichman C (2013) Anatomy of the Credit Score. J Econ Behav Organ 95: 175–185. https://doi.org/10.1016/j.jebo.2011.05.005 doi: 10.1016/j.jebo.2011.05.005
|
| [4] |
Baesens B, Van Gestel T, Viaene S, et al. (2003) Benchmarking state-of-the-art classification algorithms for credit scoring. J Oper Res Soc 54: 627–635. https://doi.org/10.1057/palgrave.jors.2601545 doi: 10.1057/palgrave.jors.2601545
|
| [5] |
Baesens B, Gestel TV, Stepanova M, et al. (2004) Neural Network Survival Analysis for Personal Loan Data. J Oper Res Soc 56: 1089–1098. https://doi.org/10.1057/palgrave.jors.2601990 doi: 10.1057/palgrave.jors.2601990
|
| [6] | Bishop CM (2006) Pattern Recognition and Machine Learning, Springer. https://doi.org/10.1007/978-0-387-45528-0_5 |
| [7] | Bolton C (2010) Logistic Regression and its Application in Credit Scoring, University of Pretoria. Available from: http://hdl.handle.net/2263/27333. |
| [8] |
Breiman L (1996) Bagging Predictors. Mach Learn 24: 123–140. https://doi.org/10.1007/BF00058655 doi: 10.1007/BF00058655
|
| [9] | Breiman L, Friedman J, Stone CJ, et al. (1984) Classification and Regression Trees, Taylor & Francis. https://doi.org/10.1201/9781315139470 |
| [10] | Brown M, Grundy M, Lin D, et al. (1999) Knowledge-Base Analysis of Microarray Gene Expression Data Using Support Vector Machines, University of California in Santa Cruz. https://doi.org/10.1073/pnas.97.1.262 |
| [11] | Byanjankar A, Heikkilä M, Mezei J (2015) Predicting credit risk in peer-to-peer lending: A neural network approach. In 2015 IEEE symposium series on computational intelligence, IEEE, 719–725. https://doi.org/10.1109/SSCI.2015.109 |
| [12] |
Cao A, He H, Chen Z, et al. (2018) Performance evaluation of machine learning approaches for credit scoring. Int J Econ Financ Manage Sci 6: 255–260. https://doi.org/10.11648/j.ijefm.20180606.12 doi: 10.11648/j.ijefm.20180606.12
|
| [13] | Chen S, Wang Q, Liu S (2019) Credit risk prediction in peer-to-peer lending with ensemble learning framework. In 2019 Chinese Control And Decision Conference (CCDC), IEEE, 4373–4377. https://doi.org/10.1109/CCDC.2019.8832412 |
| [14] | Chen TQ, Guestrin C (2016) XGBoost: A Scalable Tree Boosting System. KDD'16 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785 |
| [15] |
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20: 273–297. https://doi.org/10.1007/BF00994018 doi: 10.1007/BF00994018
|
| [16] | Crouhy M, Galai D, Mark R (2014) The Essentials of Risk Management, 2nd Edition. McGraw-Hill. Available from: https://www.mhprofessional.com/9780071818513-usa-the-essentials-of-risk-management-second-edition-group. |
| [17] |
Cybenko G (1989) Approximation by Superpositions of a Sigmoidal Function Mathematics of Control. Signals Syst 2: 303–314. https://doi.org/10.1007/BF02551274 doi: 10.1007/BF02551274
|
| [18] |
Duan J (2019) Financial system modeling using deep neural networks (DNNs) for effective risk assessment and prediction. J Franklin Inst 356: 4716–4731. https://doi.org/10.1016/j.jfranklin.2019.01.046 doi: 10.1016/j.jfranklin.2019.01.046
|
| [19] |
Duchi J, Hazan E, Singer Y (2011) Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. J Mach Learn Rese 12: 2121–2159. https://doi.org/10.5555/1953048.2021068 doi: 10.5555/1953048.2021068
|
| [20] | Elrahman SMA, Abraham A (2013) A Review of Class Imbalance Problem. J Network Innov Comput 1: 332–340. http://ias04.softcomputing.net/jnic2.pdf |
| [21] |
Everett CR (2015) Group Membership, Relationship Banking and Loan Default Risk: the Case of Online Social Lending. Bank Financ Rev 7: 15–54. https://doi.org/10.2139/ssrn.1114428 doi: 10.2139/ssrn.1114428
|
| [22] |
Friedman JH (2001) Greedy Function Approximation: A Gradient Boosting Machine. Ann Stat 29: 1189–1232. https://doi.org/10.1214/aos/1013203451 doi: 10.1214/aos/1013203451
|
| [23] |
Genuer R, Poggi JM, Tuleau-Malot C (2010) Variable selection Using Random Forests. Pattern Recogn Lett 31: 2225–2236. https://doi.org/10.1016/j.patrec.2010.03.014 doi: 10.1016/j.patrec.2010.03.014
|
| [24] | Glorot X, Bengio Y (2010) Understanding the Difficulty of Training Deep Feedforward Neural Networks. J Mach Learn Res 9: 249–256. http://proceedings.mlr.press/v9/glorot10a.html |
| [25] | Guyon I, ElNoeeff A (2003) An Introduction to Variable and Feature Selection. J Mach Learn Res 3: 1157–1182. https://www.jmlr.org/papers/v3/guyon03a.html |
| [26] | Hastie T, Tibshirani R, Friedman JH (2009) The elements of statistical learning: data mining, inference, and prediction, Springer. https://doi.org/10.1007/978-0-387-84858-7 |
| [27] | He KM, Zhang XY, Ren SQ, et al. (2015) Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. IEEE international conference on computer vision. https://doi.org/10.1109/ICCV.2015.123 |
| [28] | Ho TK (1995) Random Decision Forest, Proceeding of the 3rd International Conference on Document Analysis and Recognition, 278–282. https://doi.org/10.1109/ICDAR.1995.598994 |
| [29] |
Ho TK (1998) The Random Subspace Method for Constructing Decision Forests. IEEE T Pattern Anal 20: 832–844. https://doi.org/10.1109/34.709601 doi: 10.1109/34.709601
|
| [30] | Hochreiter S, Bengio Y, Frasconi P, et al. (2001) Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies. In A Field Guide to Dynamical Recurrent Networks, IEEE, 237–243. https://doi.org/10.1109/9780470544037.ch14. |
| [31] | Hsu CW, Chang CC, Lin CJ (2003) A Practical Guide to Support Vector Classification. National Taiwan University, 1–12. Available from: https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf. |
| [32] |
Ioffe S, Szegedy C (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. International conference on machine learning, 448–456. https://doi.org/10.48550/arXiv.1502.03167 doi: 10.48550/arXiv.1502.03167
|
| [33] | Iyer R, Khwaja AI, Luttmer EF, et al. (2009) Screening in New Credit Markets: Can Individual Lenders Infer Borrower Creditworthiness in Peer-to-Peer Lending? AFA 2011 Denver Meetings Paper. https://doi.org/10.2139/ssrn.1570115 |
| [34] |
Kang H (2013) The Prevention and Handling of the Missing Data. Korean J Anesthesiol 64: 402–406. https://doi.org/10.4097/kjae.2013.64.5.402 doi: 10.4097/kjae.2013.64.5.402
|
| [35] | Ke GL, Meng Q, Finley T, et al. (2017) LightGBM: A highly Efficient Gradient Boosting Decision Tree, Neural Information Processing Systems, 3149–3157. Available from: https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf. |
| [36] | Keogh E, Mueen A (2017) Curse of Dimensionality. Encyclopedia of Machine Learning and Data Mining, Boston: Springer. https://doi.org/10.1007/978-1-4899-7687-1_192 |
| [37] | Kingma DP, Ba JL (2015) Adam: a Method for Stochastic Optimization. International Conference on Learning Representations, 1–13. https://doi.org/10.48550/arXiv.1412.6980 |
| [38] | Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems, 1097–1105. https://doi.org/10.1145/3065386 |
| [39] | Lantz B (2013) Machine Learning with R. Packt Publishing Limited. Available from: https://edu.kpfu.ru/pluginfile.php/278552/mod_resource/content/1/MachineLearningR__Brett_Lantz.pdf. |
| [40] | Li LH, Sharma AK, Ahmad R, Chen RC (2021) Predicting the Default Borrowers in P2P Platform Using Machine Learning Models. In International Conference on Artificial Intelligence and Sustainable Computing. https://doi.org/10.1007/978-3-030-82322-1_20 |
| [41] | Lin HT, Lin CJ (2003) A Study on Sigmoid Kernels for SVM and the Training of Non-PSD Kernels by SMO-type Methods. National Taiwan University. Available from: https://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf |
| [42] | Lu L, Shin YJ, Su YH, et al. (2019) Dying ReLU and Initialization: Theory and Numerical Examples. arXiv preprint arXiv: 1903.06733. https://doi.org/10.4208/cicp.OA-2020-0165 |
| [43] | Maas AL, Hannun AY, Ng AY (2013) Rectifier Nonlinearities Improve Neural Network Acoustic Models. ICML Workshop on Deep Learning for Audio, Speech, and Language Processing. Available from: https://ai.stanford.edu/~amaas/papers/relu_hybrid_icml2013_final.pdf. |
| [44] | Madasamy K, Ramaswami M (2017) Data Imbalance and Classifiers: Impact and Solutions from a Big Data Perspective. Int J Comput Intell Res 13: 2267–2281. Available from: https://www.ripublication.com/ijcir17/ijcirv13n9_09.pdf. |
| [45] |
McCulloch WS, Pitts W (1943) A Logical Calculus of the Ideas Immanent in Nervous Activity. Bull Math Biophys 5: 115–133. https://doi.org/10.2307/2268029 doi: 10.2307/2268029
|
| [46] | Mester LJ (1997) What's the Point of Credit Scoring? Bus Rev 3: 3–16. Available from: https://www.philadelphiafed.org/-/media/frbp/assets/economy/articles/business-review/1997/september-october/brso97lm.pdf. |
| [47] | Mijwel MM (2018) Artificial Neural Networks Advantages and Disadvantages. Available from: https://www.linkedin.com/pulse/artificial-neural-networks-advantages-disadvantages-maad-m-mijwel/. |
| [48] | Mills KG, McCarthy B (2016) The State of Small Business Lending: Innovation and Technology and the Implications for Regulation. HBS Working Paper No. 17-042. https://doi.org/10.2139/ssrn.2877201 |
| [49] |
Mountcastle VB (1957) Modality and Topographic Properties of Single Neurons of Cat's Somatic Sensory Cortex. J Neurophysiol 20: 408–434. https://doi.org/10.1152/jn.1957.20.4.408 doi: 10.1152/jn.1957.20.4.408
|
| [50] |
Ohlson JA (1980) Financial Ratios and the Probabilistic Prediction of Bankruptcy. J Account Res 18: 109–131. https://doi.org/10.2307/2490395 doi: 10.2307/2490395
|
| [51] | Patro SGK, Sahu KK (2015) Normalization: A Preprocessing Stage. https://doi.org/10.17148/IARJSET.2015.2305 |
| [52] |
Pontil M, Verri A (1998) Support Vector Machines for 3D Object Recognition. IEEE Trans PAMI 20: 637–646. https://doi.org/10.1109/34.683777 doi: 10.1109/34.683777
|
| [53] |
Qian N (1999) On the Momentum Term in Gradient Descent Learning Algorithms. Neural Networks 12: 145–151. https://doi.org/10.1016/S0893-6080(98)00116-6 doi: 10.1016/S0893-6080(98)00116-6
|
| [54] |
Quinlan JR (1987) Simplifying Decision Trees. Int J Man-Mach Stud 27: 221–234. https://doi.org/10.1016/S0020-7373(87)80053-6 doi: 10.1016/S0020-7373(87)80053-6
|
| [55] | Quinlan JR (1992) C4.5: Programs for Machine Learning. San Mateo: Morgan Kaufmann Publishers Inc. Available from: https://www.elsevier.com/books/c45/quinlan/978-0-08-050058-4. |
| [56] |
Rajan U, Seru A, Vig V (2015) The Failure of Models that Predict Failure: Distance, Incentives, and Defaults. J Financ Econ 115: 237–260. https://doi.org/10.1016/j.jfineco.2014.09.012 doi: 10.1016/j.jfineco.2014.09.012
|
| [57] |
Rosenblatt F (1958) The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain. Psychol Rev 65: 386–408. https://doi.org/10.1037/h0042519 doi: 10.1037/h0042519
|
| [58] | Ruder S (2017) An Overview of Gradient Descent Optimization Algorithms. arXiv preprint arXiv: 1609.04747. https://doi.org/10.6919/ICJE.202102_7(2).0058 |
| [59] |
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning Representations by Back-Propagating Errors. Nature 323: 533–536. https://doi.org/10.1038/323533a0 doi: 10.1038/323533a0
|
| [60] | Samitsu A (2017) The Structure of P2P Lending and Legal Arrangements: Focusing on P2P Lending Regulation in the UK. IMES Discussion Paper Series, No. 17-J-3. Available from: https://www.boj.or.jp/en/research/wps_rev/lab/lab17e06.htm/ |
| [61] | Serrano-Cinca C, Gutierrez-Nieto B, López-Palacios L (2015) Determinants of Default in P2P Lending. PloS One 10: e0139427. https://doi.org/10.1371/journal.pone.0139427 |
| [62] |
Serrano-Cinca C, Gutiérrez-Nieto B (2016) The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending. Deci Support Syst 89: 113–122. https://doi.org/10.1016/j.dss.2016.06.014 doi: 10.1016/j.dss.2016.06.014
|
| [63] |
Shannon C (1948) A Mathematical Theory of Communication. Bell Syst Tech J 27: 379–423. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x doi: 10.1002/j.1538-7305.1948.tb01338.x
|
| [64] | Shelke MS, Deshmukh PR, Shandilya VK (2017) A Review on Imbalanced Data Handling using Undersampling and Oversampling Technique. Int J Recent Trends Eng Res. https://doi.org/10.23883/IJRTER.2017.3168.0UWXM |
| [65] | Singh S, Gupta P (2014) Comparative Study Id3, Cart and C4.5 Decision Tree Algorithm: A Survey. Int J Adv Inf Sci Technol (IJAIST) 27: 97–103. https://doi.org/10.15693/ijaist/2014.v3i7.47-52 |
| [66] | Srivastava N, Hinton G, Krizhevsky A, et al. (2014) Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J Mach Learn Res 15: 1929–1958. https://doi.org/https://jmlr.org/papers/v15/srivastava14a.html |
| [67] |
Thomas LC (2000) A Survey of Credit and Behavioural Scoring: Forecasting Financial Risk of Lending to Consumers. Int J Forecast 16: 149–172. https://doi.org/10.1016/S0169-2070(00)00034-0 doi: 10.1016/S0169-2070(00)00034-0
|
| [68] |
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J Royal Stat Soc (Methodological) 58: 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x doi: 10.1111/j.2517-6161.1996.tb02080.x
|
| [69] | Tieleman T, Hinton G (2012) Lecture 6.5—RMSProp, COURSERA: Neural Networks for Machine Learning. |
| [70] | Verified Market Research (2021) Global Peer to Peer (P2P) Lending Market Size by Type, by End User, by Geographic Scope and Forecast. Available from: https://www.verifiedmarketresearch.com/product/peer-to-peer-p2p-lending-market/. |
| [71] |
Wang Z, Cui P, Li FT, et al. (2014) A Data-Driven Study of Image Feature Extraction and Fusion. Inf Sci 281: 536–558. https://doi.org/10.1016/j.ins.2014.02.030 doi: 10.1016/j.ins.2014.02.030
|
| 1. | Tayebi M'hammed, Khelafi Hamid, An experimental study on the influence of arid climate on early-age cracking of concrete—A case study of the city of Adrar in Algeria, 2021, 8, 2372-0484, 200, 10.3934/matersci.2021014 | |
| 2. | Grzegorz Ludwik Golewski, Fracture Performance of Cementitious Composites Based on Quaternary Blended Cements, 2022, 15, 1996-1944, 6023, 10.3390/ma15176023 | |
| 3. | Salmia Beddu, Teh Sabariah Binti Abd Manan, Fadzli Mohamed Nazri, Nur Liyana Mohd Kamal, Daud Mohamad, Zarina Itam, Mushtaq Ahmad, Sustainable Energy Recovery From the Malaysian Coal Bottom Ash and the Effects of Fineness in Improving Concrete Properties, 2022, 10, 2296-598X, 10.3389/fenrg.2022.940883 | |
| 4. | Chengfang Yuan, Di Wang, Haris Setiawan, Yiran Wei, Effect and mechanism of different excitation modes on the activities of the recycled brick micropowder, 2021, 28, 2191-0359, 676, 10.1515/secm-2021-0062 | |
| 5. | Kowsalya. M, S. Sindhu Nachiar, Anandh. S, A review on fly ash cenosphere as a solid waste in concrete application, 2022, 68, 22147853, 2072, 10.1016/j.matpr.2022.08.363 | |
| 6. | Bartosz Szostak, Grzegorz Ludwik Golewski, Rheology of Cement Pastes with Siliceous Fly Ash and the CSH Nano-Admixture, 2021, 14, 1996-1944, 3640, 10.3390/ma14133640 | |
| 7. | Grzegorz Ludwik Golewski, Green Concrete Based on Quaternary Binders with Significant Reduced of CO2 Emissions, 2021, 14, 1996-1073, 4558, 10.3390/en14154558 | |
| 8. | Salmia Beddu, Amalina Basri, Daud Mohamad, Nur Liyana Mohd Kamal, Nur Farhana, Zakaria Che Muda, Zarina Itam, Sivakumar Naganathan, Siti Asmahani Saad, Teh Sabariah, 2022, Chapter 10, 978-981-16-5040-6, 143, 10.1007/978-981-16-5041-3_10 | |
| 9. | Grzegorz Ludwik Golewski, The Role of Pozzolanic Activity of Siliceous Fly Ash in the Formation of the Structure of Sustainable Cementitious Composites, 2022, 3, 2673-4079, 520, 10.3390/suschem3040032 | |
| 10. | Grzegorz Ludwik Golewski, Bartosz Szostak, Application of the C-S-H Phase Nucleating Agents to Improve the Performance of Sustainable Concrete Composites Containing Fly Ash for Use in the Precast Concrete Industry, 2021, 14, 1996-1944, 6514, 10.3390/ma14216514 | |
| 11. | Grzegorz Ludwik Golewski, Combined Effect of Coal Fly Ash (CFA) and Nanosilica (nS) on the Strength Parameters and Microstructural Properties of Eco-Friendly Concrete, 2022, 16, 1996-1073, 452, 10.3390/en16010452 | |
| 12. | M. Jayadurgalakshmi, S. Kandasamy, A comparative study on the various alternative materials for fine aggregate in concrete, 2022, 65, 22147853, 1614, 10.1016/j.matpr.2022.04.670 | |
| 13. | Vaibhav Sharma, Subhakanta Dash, Piyush Gupta, Comprehensive Review of Fly Ash: Environmental Impact and Applications, 2024, 34, 1088-1913, 10.1002/tqem.22338 | |
| 14. | Daud Mohamad, Salmia Beddu, Nur Liyana Mohd Kamal, Seleman Karim, S. Nagappan, N. Sivakumar, The combination of conventional Roller Compacted Concrete (RCC) with the substitution of fly ash for fine aggregate replacement, 2024, 400, 2261-236X, 01006, 10.1051/matecconf/202440001006 | |
| 15. | Christin Jose, Ganga Radhakrishnan, Abhinav Anandan, Althaf T A, Sankar B, K. Arunkumar, D. Ramesh Kumar, P. Swaminathan, B. Sankar, Review of Mechanical, Durability, and Thermal properties of Light weight concrete containing cenosphere, 2024, 529, 2267-1242, 01032, 10.1051/e3sconf/202452901032 | |
| 16. | Salmia Beddu, Nur Amalina Nadiah Basri, Nur Liyana Mohd Kamal, Daud Mohamad, Zarina Itam, N. Sivakumar, Warid Wazien Ahmad Zailani, Fadzli Mohamed Nazri, S. Nagappan, N. Sivakumar, Characterization of Coal Combustion Products from Malaysian Power Plant for Building Materials Applications, 2024, 400, 2261-236X, 01007, 10.1051/matecconf/202440001007 | |
| 17. | Nilesh Zanjad, Shantanu Pawar, Chittaranjan Nayak, Review on Application of Lightweight Cenosphere in Construction Material, 2024, 413, 1022-1360, 10.1002/masy.202300006 |
Figures(2) / Tables(8)
An-Hsing Chang, Li-Kai Yang, Rua-Huan Tsaih, Shih-Kuei Lin. Machine learning and artificial neural networks to construct P2P lending credit-scoring model: A case using Lending Club data[J]. Quantitative Finance and Economics, 2022, 6(2): 303-325. doi: 10.3934/QFE.2022013
| Chemical property | Percentage (%) | Physical property | Results |
| CaO | 60.7 | Size | ≤75 µ |
| SiO2 | 21.9 | Fineness | 91% |
| Al2O3 | 7.4 | Normal consistency | 26% |
| Fe2O3 | 5.7 | Initial stetting time | 33 min |
| MgO | 4.5 | Final stetting time | 408 min |
| SO3 | 3.9 | Specific surface | 322 m2/kg |
| K2O | 2.4 | Soundness | 1.30% |
| Na2O | 0.2 | 28-days compressive strength | 42 MPa |
DownLoad:
CSV
| Physical property | Fine aggregate | Coarse aggregate |
| Particle size (mm) | 4.75-0.075 | 19.5-4.75 |
| Fineness modulus | 2.83 | 4.3 |
| Absorption capacity (%) | 5.08 | 3.13 |
| Moisture content (%) | 2.8 | 1.25 |
| Bulk density (kg/m3) | 1586 | 1565 |
DownLoad:
CSV
| Control sample (0%) | Cenesphere (10%) | Cenesphere (20%) | Cenosphere (30%) | |
| Ingredients (kg) | 3.06 | 6.12 | 9.18 | |
| Cement (kg) | 15.80 | 15.80 | 15.80 | 15.80 |
| Sand (kg) | 30.60 | 27.54 | 24.48 | 21.42 |
| LECA (kg) | 25.4 | 25.4 | 25.4 | 25.4 |
| Water | 7.9 | 7.9 | 7.9 | 7.9 |
| Polypropylene fiber | 0.079 | 0.079 | 0.079 | 0.079 |
DownLoad:
CSV
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 3 | Control | 1 | 4.4 |
| 2 | 5.0 | ||
| 3 | 5.1 | ||
| 10% CE | 1 | 6.1 | |
| 2 | 7.4 | ||
| 3 | 5.8 | ||
| 20% CE | 1 | 10.6 | |
| 2 | 16.9 | ||
| 3 | 23.9 | ||
| 30% CE | 1 | 11.6 | |
| 2 | 14.2 | ||
| 3 | 5.3 |
DownLoad:
CSV
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 7 | Control | 1 | 8.7 |
| 2 | 9.9 | ||
| 3 | 10.6 | ||
| 10% CE | 1 | 14.6 | |
| 2 | 19.8 | ||
| 3 | 18.3 | ||
| 20% CE | 1 | 20.4 | |
| 2 | 25.4 | ||
| 3 | 18.2 | ||
| 30% CE | 1 | 11.7 | |
| 2 | 12.2 | ||
| 3 | 14.3 |
DownLoad:
CSV
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 28 | Control | 1 | 11.6 |
| 2 | 14.2 | ||
| 3 | 5.3 | ||
| 10% CE | 1 | 28.8 | |
| 2 | 27.3 | ||
| 3 | 24.5 | ||
| 20% CE | 1 | 28.8 | |
| 2 | 25.5 | ||
| 3 | 27.0 | ||
| 30% CE | 1 | 21.9 | |
| 2 | 17.7 | ||
| 3 | 18.5 |
DownLoad:
CSV
| Mix design | Sample No. | Splitting strength (MPa) | Average strength (MPa) |
| 0% CE | 1 | 1.003 | 1.131 |
| 2 | 1.274 | ||
| 3 | 1.117 | ||
| 10% CE | 1 | 2.321 | 2.180 |
| 2 | 2.187 | ||
| 3 | 2.033 | ||
| 20% CE | 1 | 1.649 | 1.732 |
| 2 | 2.011 | ||
| 3 | 1.535 | ||
| 30% CE | 1 | 1.341 | 1.250 |
| 2 | 1.357 | ||
| 3 | 1.051 |
DownLoad:
CSV
| Design mix | Average TC (W/mK) | Average density (kg/m3) |
| Control sample | 1.2873 | 1896.5 |
| 10% cenosphere | 1.0795 | 1895.0 |
| 20% cenosphere | 0.9463 | 1827 |
| 30% cenosphere | 0.8445 | 1592.9 |
DownLoad:
CSV
| Chemical property | Percentage (%) | Physical property | Results |
| CaO | 60.7 | Size | ≤75 µ |
| SiO2 | 21.9 | Fineness | 91% |
| Al2O3 | 7.4 | Normal consistency | 26% |
| Fe2O3 | 5.7 | Initial stetting time | 33 min |
| MgO | 4.5 | Final stetting time | 408 min |
| SO3 | 3.9 | Specific surface | 322 m2/kg |
| K2O | 2.4 | Soundness | 1.30% |
| Na2O | 0.2 | 28-days compressive strength | 42 MPa |
| Physical property | Fine aggregate | Coarse aggregate |
| Particle size (mm) | 4.75-0.075 | 19.5-4.75 |
| Fineness modulus | 2.83 | 4.3 |
| Absorption capacity (%) | 5.08 | 3.13 |
| Moisture content (%) | 2.8 | 1.25 |
| Bulk density (kg/m3) | 1586 | 1565 |
| Control sample (0%) | Cenesphere (10%) | Cenesphere (20%) | Cenosphere (30%) | |
| Ingredients (kg) | 3.06 | 6.12 | 9.18 | |
| Cement (kg) | 15.80 | 15.80 | 15.80 | 15.80 |
| Sand (kg) | 30.60 | 27.54 | 24.48 | 21.42 |
| LECA (kg) | 25.4 | 25.4 | 25.4 | 25.4 |
| Water | 7.9 | 7.9 | 7.9 | 7.9 |
| Polypropylene fiber | 0.079 | 0.079 | 0.079 | 0.079 |
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 3 | Control | 1 | 4.4 |
| 2 | 5.0 | ||
| 3 | 5.1 | ||
| 10% CE | 1 | 6.1 | |
| 2 | 7.4 | ||
| 3 | 5.8 | ||
| 20% CE | 1 | 10.6 | |
| 2 | 16.9 | ||
| 3 | 23.9 | ||
| 30% CE | 1 | 11.6 | |
| 2 | 14.2 | ||
| 3 | 5.3 |
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 7 | Control | 1 | 8.7 |
| 2 | 9.9 | ||
| 3 | 10.6 | ||
| 10% CE | 1 | 14.6 | |
| 2 | 19.8 | ||
| 3 | 18.3 | ||
| 20% CE | 1 | 20.4 | |
| 2 | 25.4 | ||
| 3 | 18.2 | ||
| 30% CE | 1 | 11.7 | |
| 2 | 12.2 | ||
| 3 | 14.3 |
| No. of days | Mix design | Specimen No. | Strength (MPa) |
| 28 | Control | 1 | 11.6 |
| 2 | 14.2 | ||
| 3 | 5.3 | ||
| 10% CE | 1 | 28.8 | |
| 2 | 27.3 | ||
| 3 | 24.5 | ||
| 20% CE | 1 | 28.8 | |
| 2 | 25.5 | ||
| 3 | 27.0 | ||
| 30% CE | 1 | 21.9 | |
| 2 | 17.7 | ||
| 3 | 18.5 |
| Mix design | Sample No. | Splitting strength (MPa) | Average strength (MPa) |
| 0% CE | 1 | 1.003 | 1.131 |
| 2 | 1.274 | ||
| 3 | 1.117 | ||
| 10% CE | 1 | 2.321 | 2.180 |
| 2 | 2.187 | ||
| 3 | 2.033 | ||
| 20% CE | 1 | 1.649 | 1.732 |
| 2 | 2.011 | ||
| 3 | 1.535 | ||
| 30% CE | 1 | 1.341 | 1.250 |
| 2 | 1.357 | ||
| 3 | 1.051 |
| Design mix | Average TC (W/mK) | Average density (kg/m3) |
| Control sample | 1.2873 | 1896.5 |
| 10% cenosphere | 1.0795 | 1895.0 |
| 20% cenosphere | 0.9463 | 1827 |
| 30% cenosphere | 0.8445 | 1592.9 |
