Accurate gender prediction is crucial for businesses to offer personalized services to their customers. To address the issue of low prediction accuracy typically associated with traditional machine learning techniques in commercial recommendation systems, a parallel hybrid prediction model was proposed. This model combines convolutional neural networks (CNNs), bidirectional long short-term memory (BiLSTM) networks, and an attention mechanism, forming a hybrid CNN-BiLSTM-attention mechanism model. By leveraging the CNN's ability to capture local features, the BiLSTM's strength in processing the contextual information of sequential data, and the attention mechanism's focus on relevant data, the model improves gender prediction accuracy. Additionally, the research utilized the ANOVA method and random forest models to extract relevant features, applied the continuous bag of word (CBOW) algorithm to vectorize clickstream text data, and employs the parallel CNN-BiLSTM-attention mechanism model for gender prediction. The results show that this proposed model outperforms individual models in gender prediction accuracy. This development establishes a strong foundation for merchant recommendation systems, allowing them to deliver more accurate service recommendations.
Citation: Zichang Wang, Xiaoping Lu. Gender prediction model based on CNN-BiLSTM-attention hybrid[J]. Electronic Research Archive, 2025, 33(4): 2366-2390. doi: 10.3934/era.2025105
Accurate gender prediction is crucial for businesses to offer personalized services to their customers. To address the issue of low prediction accuracy typically associated with traditional machine learning techniques in commercial recommendation systems, a parallel hybrid prediction model was proposed. This model combines convolutional neural networks (CNNs), bidirectional long short-term memory (BiLSTM) networks, and an attention mechanism, forming a hybrid CNN-BiLSTM-attention mechanism model. By leveraging the CNN's ability to capture local features, the BiLSTM's strength in processing the contextual information of sequential data, and the attention mechanism's focus on relevant data, the model improves gender prediction accuracy. Additionally, the research utilized the ANOVA method and random forest models to extract relevant features, applied the continuous bag of word (CBOW) algorithm to vectorize clickstream text data, and employs the parallel CNN-BiLSTM-attention mechanism model for gender prediction. The results show that this proposed model outperforms individual models in gender prediction accuracy. This development establishes a strong foundation for merchant recommendation systems, allowing them to deliver more accurate service recommendations.
| [1] |
W. Nadeem, D. Andreini, J. Salo, T. Laukkanen, Engaging consumers online through websites and social media: A gender study of Italian generation Y clothing consumers, Int. J. Inf. Manage., 35 (2015), 16–64. http://doi.org/10.1016/j.ijinfomgt.2015.04.008 doi: 10.1016/j.ijinfomgt.2015.04.008
|
| [2] | B. Hasan, Exploring gender differences in online shopping attitude, Comput. Hum. Behav., 26 (2010), 33–74. http://doi.org/10.1016/j.chb.2009.12.012, 596–601. |
| [3] |
M.Zhou, Gender difference in web search perceptions and behavior: Does it vary by task performance?, Comput. Educ., 78 (2014), 174–184. http://doi.org/10.1016/j.compedu.2014.06.005 doi: 10.1016/j.compedu.2014.06.005
|
| [4] |
C. McLaughlin, L. Bradley, G. Prentice, E. J. Verner, S. Loane Gender differences using online auctions within a generation Y sample: An application of the theory of planned behaviour, J. Retailing Consum. Services., 56 (2020), 1–13. http://doi.org/10.1016/j.jretconser.2020.102181 doi: 10.1016/j.jretconser.2020.102181
|
| [5] |
Z. Huang, J. Mou, Gender differences in user perception of usability and performance of online travel agency websites, Technol. Soc., 66 (2021). http://doi.org/10.1016/j.techsoc.2021.101671 doi: 10.1016/j.techsoc.2021.101671
|
| [6] | S. Choudhary, M. Agarwal, Framework for gender recognition using facial features by using deep learning, in Second International Conference on Image Processing and Capsule Networks: ICIPCN 2021, 300 (2022), 599–608. https://doi.org/10.1007/978-3-030-84760-9_51 |
| [7] |
T. Van Hamme, G. Garofalo, E. Argones Rúa, D. Preuveneers, W. Joosen, A systematic comparison of age and gender prediction on imu sensor-based gait traces, Sensors, 19 (2019), 2945–2961. https://doi.org/10.3390/s19132945 doi: 10.3390/s19132945
|
| [8] |
S. Haseena, S. Saroja, R. Madavan, A. Karthick, B. Pant, M. Kifetew, Prediction of the age and gender based on human face images based on deep learning algorithm, Comput. Math. Methods Med., 2022 (2022). https://doi.org/10.1155/2022/1413597 doi: 10.1155/2022/1413597
|
| [9] |
M. M. Islam, J. H. Baek, Deep learning based real age and gender estimation from unconstrained face image towards smart store customer relationship management, Appl. Sci., 11 (2021), 4549. http://doi.org/10.3390/app11104549 doi: 10.3390/app11104549
|
| [10] | K. ELKarazle, V. Raman, P. Then, Facial gender classification using deep learning, in Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition., 417 (2022), 598–607. http://doi.org/10.1007/978-3-030-96302-6. |
| [11] |
G. Yasmin, A. K. Das, J. Nayak, S. Vimal, S. Dutta, A rough set theory and deep learning-based predictive system for gender recognition using audio speech, Soft Comput., 28 (2022), 1–24. http://doi.org/10.1007/s00500-022-07074. doi: 10.1007/s00500-022-07074
|
| [12] |
P. C. S. Reddy, K. Sarma, A. Sharma, P. V. Rao, S. G. Rao, G. R. Sakthidharan, et al., Enhanced age prediction and gender classification (EAP-GC) framework using regression and SVM techniques, Mater. Today Proc., 2020 (2020). http://doi.org/10.1016/j.matpr.2020.10.857. doi: 10.1016/j.matpr.2020.10.857
|
| [13] |
Y. Efea, L. Demirb, The impact of feature selection models on the accuracy of tree-based classification algorithms: Heart disease case, Proc. Comput. Sci., 253 (2025), 757–764. https://doi.org/10.1016/j.procs.2025.01.1. doi: 10.1016/j.procs.2025.01.1
|
| [14] | Z. Wang, Research on feature selection methods based on random forest, Tehnički Vjesnik, 30 (2023), 623–633. |
| [15] |
M. A. Rahman, M. R. Islam, M. A. H. Rafath, S. Mhejabin, CNN based covid-19 detection from image processing, J. ICT Res. Appl., 17 (2023). http://doi.org/10.5614/itbj.ict.res.appl.2023.17.1.7 doi: 10.5614/itbj.ict.res.appl.2023.17.1.7
|
| [16] | A. Briot, P. Viswanath, S. Yogamani, Analysis of efficient cnn design techniques for semantic segmentation, in IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018 (2018), 1065–1089. http://doi.org/10.1007/978-3-030-01234-2_1 |
| [17] |
A. Anton, N. F. Nissa, A. Janiati, N. Cahya, P Astuti, Application of deep learning using convolutional neural network (CNN) method for Women’ s skin classification, Sci. J. Inf., 8 (2021), 144–153. http://doi.org/10.15294/sji.v8i1.26888 doi: 10.15294/sji.v8i1.26888
|
| [18] | A. Kumar, R. Mamgai, R. Jain, Application of IoT-enabled CNN for natural language processing, in IoT-enabled Convolutional Neural Networks: Techniques and Applications, River Publishers, (2023), 149–177. https://doi.org/10.1201/9781003393030-6 |
| [19] | A. Dutt, P. Gader, Wavelet multiresolution analysis based speech emotion recognition system using 1D CNN LSTM networks, in IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31 (2023), 1–12. http://doi.org/10.1109/TASLP.2023.3277291 |
| [20] |
J. Ramesh, R. Manavalan, Prostate ultrasound image classification using CNN-BILSTM, Indian J. Comput. Sci. Eng., 12 (2021), 1611–1620. http://doi.org/10.21817/indjcse/2021/v12i6/211206028 doi: 10.21817/indjcse/2021/v12i6/211206028
|
| [21] | D. H. Fudholi, R. A. N. Nayoan, A. F. Hidayatullah, D. B. Arianto, A hybrid cnn-BiLSTM model for drug named entity recognition, J. Eng. Sci. Technol., 17 (2022), 730–744. |
| [22] |
M. Yanga, J. Wang, Adaptability of financial time series prediction based on BiLSTM, Proc. Comput. Sci., 199 (2022), 18–25. http://doi.org/10.1016/j.procs.2022.01.003 doi: 10.1016/j.procs.2022.01.003
|
| [23] |
J. J. Ren, H. Wei, Z. L. Zou, T. T. Hou, Y. L. Yuan, J. Q. Shen, et al., Ultra-short-termpower load forecasting based on CNN-BiLSTM-attention, Power Syst. Prot. Control, 50 (2022), 108–116. https://doi.org/10.19783/j.cnki.pspc.211187 doi: 10.19783/j.cnki.pspc.211187
|
| [24] |
Q. H. Kha, T. O. Tran, V. N. Nguyen, K. Than, N. Q. K. Le, An interpretable deep learning model for classifying adaptor protein complexes from sequence information, Methods, 207 (2022), 90–96. https://doi: 10.1016/j.ymeth.2022.09.007 doi: https://doi: 10.1016/j.ymeth.2022.09.007
|
| [25] |
Q. H. Kha, V. H. Le, T. N. K. Hung, N. Q. K. Le, Development and validation of an efficient MRI radiomics signature for improving the predictive performance of 1p/19q co-deletion in lower-grade gliomas, Cancers, 21 (2021), 5398. https://doi.org/10.3390/cancers13215398 doi: 10.3390/cancers13215398
|
| [26] |
S. Madan, M. Lentzen, J. Brandt, D. Rueckert, M. Hofmann-Apitius, H. Fröhlich, Transformer models in biomedicine, BMC Med. Inf. Decis. Making, 24 (2024), 214. https://doi.org/10.1186/s12911-024-02600-5 doi: 10.1186/s12911-024-02600-5
|
Figures(9) / Tables(8)
Zichang Wang, Xiaoping Lu. Gender prediction model based on CNN-BiLSTM-attention hybrid[J]. Electronic Research Archive, 2025, 33(4): 2366-2390. doi: 10.3934/era.2025105
DownLoad: