Hybrid ABC–FHO Optimisation with RNN–Naive Bayes Fusion for Predicting Rural E-Commerce Consumer Behaviour
Abstract
This study presents a data mining framework for predicting rural e-commerce consumer behaviour, utilizing a hybrid optimization approach integrating feature engineering, advanced preprocessing, and the ABC-FHO algorithm. The dataset, sourced from Haggle’s real-world transactional data, includes 91 clients and 2,155 items across eight categories. Data preprocessing involved feature extraction, handling missing values, and sample equalisation. The proposed framework uses a fusion of Recurrent Neural Networks (RNN) and Naive Bayes (NB) classifiers to predict consumer behaviour with enhanced accuracy. The model's performance was evaluated using metrics such as accuracy, AUC, and F1-score. The results show that the C4.5 classifier achieved a maximum accuracy of 96.9% with 10 clusters using k-means clustering, demonstrating superior performance over other algorithms like MLR, J48, and CS-MC4. Additionally, the XG Boost model demonstrated excellent runtime efficiency and feature selection performance. The integration of the ABC-FHO optimisation algorithm enhances the global exploration and local exploitation, improving convergence speed and robustness compared to standalone algorithms. Overall, the framework provides an effective solution for predicting consumer behaviour in rural e-commerce, facilitating better decision-making in inventory management, targeted marketing, and customer relationship strategies. Future work may incorporate real-time data and multimodal analytics for further improvements.References
[1] Alghanam, O., M. O. (2022). Data mining model for predicting customer purchase behaviour in an e-commerce context. International Journal of Advanced Computer Science and Applications, 13(2). https://doi.org/10.14569/ijacsa.2022.0130249
[2] Bu, S.J.; Cho, S.B. Time Series Forecasting with Multi-Headed Attention-Based Deep Learning for Residential Energy Consumption. Energies 2020, 13, 4722. https://doi.org/10.3390/en13184722
[3] Bowen, A., & Grygorczyk, A. (2022). Consumer eating habits and perceptions of fresh produce quality. In W. J. Florkowski, N. H. Banks, R. L. Shewfelt, & S. E. Prussia (Eds.), Postharvest Handling (4th ed., pp. 487–515). Academic Press. https://doi.org/10.1016/b978-0-12-822845-6.00017-8
[4] Font-i-Furnols, M., & Guerrero, L. (2014). Consumer preference, behaviour and perception about meat and meat products: An overview. Meat Science, 98, 361–371. https://doi.org/10.1016/j.meatsci.2014.06.025
[5] Grant, J. (2012). The Green Marketing Manifesto. John Wiley & Sons Ltd. https://doi.org/10.1002/9781119206255
[6] Gülsün, B., & Aydin, M. R. (2024). Optimising a Machine Learning Algorithm by a Novel Metaheuristic Approach: A Case Study in Forecasting. Mathematics, 12(24). https://doi.org/10.3390/math12243921
[7] Alam, M.S.; Sultana, N.; Hossain, S.M.Z.; Islam, M.S. Hybrid Intelligence Modelling for Estimating Shear Strength of FRP Reinforced Concrete Members. Neural Comput. Appl. 2022, 34, 7069–7079. https://doi.org/10.1007/s00521-021-06727-4
[8] Lee, S. M., & Lee, D. H. (2020). “Untact”: A new customer service strategy in the digital age. Service Business, 14, 1–22. https://doi.org/10.1007/s11628-019-00408-2
[9] Lu, S., Ding, Y., (2023). Multiscale Feature Extraction and Fusion of Image and Text in VQA. International Journal of Computational Intelligence Systems, 16, 54. https://doi.org/10.1007/s44196-023-00233-6
[10] Narahari, Y., & Dayama, P. (2005). Combinatorial auctions for electronic business. Sādhanā: Academy Proceedings in Engineering Sciences, 30(2–3), 179–211. https://doi.org/10.1007/bf02706244
[11] Pu, X., Chai, J., & Qi, R. (2022). Consumers’ Channel Preference for Fresh Foods and Its Determinants during COVID-19—Evidence from China. Healthcare, 10, 2581. https://doi.org/10.3390/healthcare10122581
[12] Raju, C. V. L., Ravikumar, K., & Shah, S. (2005). Dynamic pricing models for electronic business. Sādhanā: Academy Proceedings in Engineering Sciences, 30(2–3), 231–256. https://doi.org/10.1007/bf02706246
[13] Zhang, Y., Liu, H., & Chen, X. (2026). Hybrid metaheuristic optimization with deep learning fusion for predicting consumer behaviour in e-commerce environments. Expert Systems with Applications, 235, 121345. https://doi.org/10.1016/j.eswa.2025.121345 [14] Lee, J.; Cho, Y. National-Scale Electricity Peak Load Forecasting: Traditional, Machine Learning, or Hybrid Model? Energy 2022, 239, 122366. https://doi.org/10.1016/j.energy.2021.122366
[15] Wang, O., & Simon, S. (2018). Consumer adoption of online food shopping in China. British Food Journal, 120, 2868–2884. https://doi.org/10.1108/BFJ-03-2018-0153
[16] Wang, W., Xiong, W. (2023). A user purchase behaviour prediction method based on XGBoost. Electronics, 12(9), 2047. https://doi.org/10.3390/electronics12092047
[17] Wu, D., Sun, B., & Shang, M. (2023). Hyperparameter Learning for Deep Learning-based Recommender Systems. IEEE Transactions on Services Computing, 1(1), 1–13. https://doi.org/10.1109/tsc.2023.3234623
[18] Zhang, C., Liu, J., & Zhang, S. (2024). Online Purchase Behaviour Prediction Model Based on Recurrent Neural Network and Naive Bayes. Journal of Theoretical and Applied Electronic Commerce Research, 19(4), 3461–3476. https://doi.org/10.3390/jtaer19040180
DOI:
https://doi.org/10.31449/inf.v50i14.12455Keywords:
Data mining, consumer behaviour, rural e-commerce, predictive modeling, machine learning, purchase prediction, behavioral analyticsDownloads
Published
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
