To improve the precision of personalized selection and push of e-commerce advertising content, a personalized advertising recommendation model based on improved Multi-Task Learning (MTL) algorithm is proposed. This study uses the data set of Specific Feature keywords (SFs) clicked by users and the basic facts of users' preference for selling keywords to increase the click-through rate of advertisements by adding personalized selling keywords in the advertisement title. Combined with the click-through rate prediction task as an auxiliary task, the prediction ability of the model is enhanced. Experimental results show that the model is better than the traditional method in terms of click-through rate, recommendation accuracy and efficiency. The Area Under the Curve (AUC) value of the model reaches 0.92, which is significantly improved compared with 0.81 of the traditional models, and the recommendation efficiency is increased by 14.26%. Through large-scale online and offline experiments, the superiority of the model in several indexes is verified. The model is particularly suitable for scenarios where users have rich clicking behavior in auxiliary tasks but sparse clicking behavior in main tasks. This study provides an effective method for optimizing the advertising push of e-commerce platforms.

[1] Abhadiomhen S., Nzeh R., Ganaa E., Nwagwu H., Okereke G., and Routray S., “Supervised Shallow Multi-Task Learning: Analysis of Methods,” Neural Processing Letters, vol. 54, pp. 2491- 2508, 2022. https://doi.org/10.1007/s11063-021- 10703-7

[2] Al-Janabi S. and Al-Barmani Z., “Intelligent Multi-Level Analytics of Soft Computing Approach to Predict Water Quality Index (IM12CP-WQI),” Soft Computing, vol. 27, pp. 7831-7861, 2023. https://doi.org/10.1007/s00500- 023-07953-z

[3] Al-Janabi S. and Al-Janabi Z., “Development of Deep Learning Method for Predicting DC Power Based on Renewable Solar Energy and Multi- Parameters Function,” Neural Computing and Applications, vol. 35, pp. 15273-15294, 2023. https://doi.org/10.1007/s00521023084806

[4] Al-Janabi S., Mohammad M., and Al-Sultan A., “A New Method for Prediction of Air Pollution Based on Intelligent Computation,” Soft Computing, vol. 24, pp. 661-680, 2020. https://doi.org/10.1007/s00500-019-04495-1

[5] Bai X. and Cambazoglu B., “Impact of Response Latency on Sponsored Search,” Information Processing and Management, vol. 56, no. 1, pp. Application Analysis of Multi-Task Learning Algorithm in E-Commerce Personalized ... 313 110-129, 2019. https://doi.org/10.1016/j.ipm.2018.10.005

[6] Bhattacharyya S. and Bose I., “S-Commerce: Influence of Facebook likes on Purchases and Recommendations on a Linked E-Commerce Site,” Decision Support Systems, vol. 138, pp. 5- 13, 2020. https://doi.org/10.1016/j.dss.2020.113383

[7] Cao Z., Chu J., Hui K., and Xu H., “The Relationship between Online Referral Marketing and Price Promotion: Evidence from a Large E- Commerce Platform,” Journal of Management Information Systems, vol. 38, no. 3, pp. 855-888, 2021. https://10.1080/07421222.2021.1962597

[8] Chandrasekar P., Nourin A., Gupta A., Jyoshna B., and Sathyan D., “Modelling the Yield Stress of Fly-Ash Added Superplasticized Cement Paste at Different Temperatures Using Artificial Neural Network,” Materials Science Forum, vol. 1048, pp. 366-375, 2022. https://doi.org/10.4028/www.scientific.net/MSF. 1048.366

[9] Díez P., Muixí A., Zlotnik S., and García- González A., “Nonlinear Dimensionality Reduction for Parametric Problems: A Kernel Proper Orthogonal Decomposition,” International Journal for Numerical Methods in Engineering, vol. 122, no. 24, pp. 7306-7327, 2021. https://doi.org/10.1002/nme.6831

[10] Fieberg J., Signer J., Smith B., and Avgar T., “A ‘How to’ Guide for Interpreting Parameters in Habitat‐Selection Analyses,” Journal of Animal Ecology, vol. 90, no. 5, pp. 1027-1043, 2021. https://doi.org/10.1111/1365-2656.13441

[11] Fukuchi T., “Characteristic Features of Error in High-Order Difference Calculation of 1D Poisson Equation and Unlimited High-Accurate Calculation Under Multi-Precision Calculation,” Mathematics and Computers in Simulation, vol. 190, pp. 303-328, 2021. https://doi.org/10.1016/j.matcom.2021.05.011

[12] Gao Q. and Sun C., “Learning High Level Features with Deep Neural Network for Click Prediction in Search and Real-Time Bidding Advertising,” in Proceedings of the 8th International Conference on Computer Engineering and Networks, Shanghai, pp. 241- 252, 2018. https://doi.org/10.1007/978-3-030- 14680-1_27

[13] García-Sánchez F., Colomo-Palacios R., and Valencia-García R., “A Social-Semantic Recommender System for Advertisements,” Information Processing and Management, vol. 57, no. 2, pp. 3-16, 2019. https://doi.org/10.1016/j.ipm.2019.102153

[14] Kadhuim Z. and Al-Janabi S., “Intelligent Deep Analysis of DNA Sequences Based on FFGM to Enhancement the Performance and Reduce the Computation,” Egyptian Informatics Journal, vol. 24, no. 2, pp. 173-190, 2023. https://doi.org/10.1016/j.eij.2023.02.004

[15] Kang S., Jeong C., and Chung K., “Tree-Based Real-Time Advertisement Recommendation System in Online Broadcasting,” IEEE Access, vol. 8, pp. 192693-192702, 2020. https://doi.org/10.1109/ACCESS.2020.3031925

[16] Li H., Zhang M., Chen D., Zhang J., Yang M., and Li Z., “Image Color Rendering Based on Hinge- Cross-Entropy GAN in Internet of Medical Things,” Computer Modeling in Engineering and Science, vol. 4, pp. 779-794, 2023. https://doi.org/10.32604/cmes.2022.022369

[17] Li L., Zhu H., Zhao S., Ding G., and Lin W., “Personality-Assisted Multi-Task Learning for Generic and Personalized Image Aesthetics Assessment,” IEEE Transactions on Image Processing, vol. 29, pp. 3898-3910, 2020. https://doi.org/10.1109/TIP.2020.2968285

[18] Liu D., Liao Y., Chung Y., and Chen K., “Advertisement Recommendation Based on Personal Interests and Ad Push Fairness,” Kybernetes, vol. 48, no. 8, pp. 1586-1605, 2019. https://doi.org/10.1108/K-05-2018-0216

[19] Liu Q., Wang D., Jia Y., Luo S., and Wang C., “A Multi-Task Based Deep Learning Approach for Intrusion Detection,” Knowledge-Based Systems, vol. 238, pp. 1-12, 2022. https://doi.org/10.1016/j.knosys.2021.107852

[20] Liu Z., Wang L., and Li X., “A Multi-Attribute Personalized Recommendation Method for Manufacturing Service Composition with Combining Collaborative Filtering and Genetic Algorithm,” Journal of Manufacturing Systems, vol. 58, pp. 348-364, 2021. https://doi.org/10.1016/j.jmsy.2020.12.019

[21] Long Y., “A Face Recognition Algorithm Based on Intermediate Layers Connected by the CNN,” Journal of Circuits, Systems and Computers, vol. 31, no. 6, pp. 1-14, 2022. https://doi.org/10.1142/S0218126622501079

[22] Maatoug M., Boukhriss M., Timoumi M., Jammali A., and Bacha H., “Theoretical Study of a Mathematical Approach of a Modeling of the Solar Collector with a Parabolic Cylindrical Type Concentration Effect,” Euro-Mediterranean Journal for Environmental Integration, vol. 8, no. 2, pp. 353-364, 2023. https://doi.org/10.1111/10.1007/s41207-023- 00358-2

[23] Moreno S., Mariani V., and Dos Santos Coelho L., “Hybrid Multi-Stage Decomposition with Parametric Model Applied to Wind Speed Forecasting in Brazilian Northeast,” Renewable Energy, vol. 164, pp. 1508-1526, 2021. https://10.1016/j.renene.2020.10.126

[24] Nassif R., Vlaski S., Richard C., Chen J., and 314 The International Arab Journal of Information Technology, Vol. 22, No. 2, March 2025 Sayed A., “Multitask Learning over Graphs: An Approach for Distributed, Streaming Machine Learning,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 14-25, 2020. https://doi.org/10.1109/MSP.2020.2966273

[25] Nitu P., Coelho J., and Madiraju P., “Improvising Personalized Travel Recommendation System with Recency Effects,” Big Data Mining and Analysis, vol. 3, pp. 139-154, 2021. https://doi.org/10.26599/BDMA.2020.9020026

[26] Niu Z., Zhong G., and Yu H., “A Review on the Attention Mechanism of Deep Learning,” Neurocomputing, vol. 452, pp. 48-62, 2021. https://doi.org/10.1016/j.neucom.2021.03.091

[27] Prabhu N., Jain H., and Tripathi A., “MTL-FoUn: A Multi-Task Learning Approach to Form Understanding,” in Proceedings of the International Conference on Document Analysis and Recognition Workshops, Lausanne, pp. 377- 388, 2021. https://doi.org/10.1007/978-3-030- 86159-9_27

[28] Qu S. and Guo G., “Fast Discrete Factorization Machine for Personalized Item Recommendation,” Knowledge-Based Systems, vol. 193, pp. 4-8, 2020. https://doi.org/10.1016/j.knosys.2019.105470

[29] Ramaboa K. and Fish P., “Keyword Length and Matching Options as Indicators of Search Intent in Sponsored Search,” Information Processing and Management, vol. 54, no. 2, pp. 175-183, 2018. https://doi.org/10.1016/j.ipm.2017.11.003

[30] Sah S. and Ghosh A., “Thermal Buckling Behavior of Power and Sigmoid Functionally Graded Material Sandwich Plates Using Non Polynomial Shear Deformation Theories,” Engineering Computations: International Journal for Computer-Aided Engineering and Software, vol. 39, no. 5, pp. 1723-1751, 2022. https://doi.org/10.1108/EC-05-2021-0306

[31] Sandnes A., Grimstad B., and Kolbjrnsen O., “Multi-Task Learning for Virtual Flow Metering,” Knowledge-Based Systems, vol. 232, pp. 1-10, 2021. https://doi.org/10.48550/arXiv.2103.08713

[32] Shan L., Bai X., Liu C., Feng Y., Liu Y., and Qi Y., “Super-Resolution Reconstruction of Digital Rock CT Images Based on Residual Attention Mechanism,” Advances in Geo-Energy Research, vol. 6, no. 2, pp. 157-168, 2022. DOI:10.46690/ager.2022.02.07

[33] Singh J., “An Efficient Deep Neural Network Model for Music Classification,” International Journal of Web Science, vol. 3, no. 3, pp. 236-248, 2022. https://doi.org/10.1504/IJWS.2022.122991

[34] Valderrama-Zurián J., García-Zorita C., Marugán- Lázaro S., and Sanz-Casado E., “Comparison of MeSH Terms and Keywords Plus Terms for more Accurate Classification in Medical Research Fields, a Case Study in Cannabis Research,” Information Processing and Management, vol. 58, no. 5, pp. 1-13, 2021. https://10.1016/j.ipm.2021.102658

[35] Vera-Baquero A., Phelan O., Slowinski P., and Hannon J., “Open-Source Software as the Main Driver for Evolving Software Systems toward a Distributed and Performant E-Commerce Platform: A Zalando Fashion Store Case Study,” IT Professional, vol. 23, no. 1, pp. 34-41, 2021. https://doi.org/10.1109/MITP.2020.2994993

[36] Wang L., Hu W., Qiu H., Shang C., Zhao T., Qiu B., Ngan K., and Li H., “A Survey of Vision and Language Related Multi-Modal Task,” CAAI Artificial Intelligence Research, vol. 1, no. 2, pp. 111-136, 2022. https://10.26599/AIR.2022.9150008

[37] Wang N., Luo C., Huang X., Huang Y., and Zhan J., “DeepCS: Training a Deep Learning Model for Cervical Spondylosis Recognition on Small- Labeled Sensor Data,” Neurocomputing, vol. 472, pp. 24-34, 2022. https://doi.org/10.1016/j.neucom.2021.11.008

[38] Wang W., Wang H., Ran Z., and He R., “Learning Robust Feature Transformation for Domain Adaptation,” Pattern Recognition, vol. 114, no. 10, pp. 1-14, 2021. https://doi.org/10.1016/j.patcog.2021.107870

[39] Weng L., Elsawah A., and Fang K., “Cross- Entropy Loss for Recommending Efficient Fold- Over Technique,” Journal of Systems Science and Complexity, vol. 34, no. 1, pp. 402-439, 2021. https://doi.org/10.1007/s11424-020-9267-9

[40] Wu T., Li Y., and Wang Y., “Personalized Recommendation System of UGC (User Generated Content) Video Resources Based on User Interest Graphs,” Francis Academic Press, vol. 3, no. 1, pp. 142-149, 2020. https://doi.org/10.25236/AJCIS.2020.030115

[41] Xie Y., Jiang D., Wang X., and Xu R., “Robust Transfer Integrated Locally Kernel Embedding for Click-Through Rate Prediction,” Information Sciences, vol. 491, pp. 190-203, 2019. https://doi.org/10.1016/j.ins.2019.04.006

[42] Xu Y., Qin H., Huang J., and Wang Y., “An End- to-End Deep Context Gate Convolutional Visual Odometry System Based on Lightweight Attention Mechanism,” Industrial Robot, vol. 49, no. 1, pp. 47-53, 2022. https://doi.org/10.1108/IR- 01-2021-0019

[43] Yakoh T. and Oi M., “Re‐Shooting Resistant Blind Watermarking Framework Based on Feature Separation with Gaussian Mixture Model,” IEEJ Transactions on Electrical and Electronic Engineering, vol. 17, no. 4, pp. 556- 565, 2022. https://doi.org/10.1002/tee.23541

[44] Yang A., Su Y., Wang Z., Jin S., Ren J., Zhang X., Shen W., and Clark J., “A Multi-Task Deep Learning Neural Network for Predicting Application Analysis of Multi-Task Learning Algorithm in E-Commerce Personalized ... 315 Flammability-Related Properties from Molecular Structures,” Green Chemistry, vol. 23, no. 12, pp. 4451-4465, 2021. https://doi.org/10.1039/D1GC00331C

[45] Ying Y., Zhang N., He P., and Peng S., “Improving Convolutional Neural Networks with Competitive Activation Function,” Security and Communication Networks, vol. 2023, pp. 1-9, 2023. https://doi.org/10.1155/2021/1933490

[46] Zhang Y., Li M., Wang S., Dai S., Luo L., Zhu E., Xu H., and Zhou H., “Gaussian Mixture Model Clustering with Incomplete Data,” ACM Transactions on Multimedia Computing Communications and Applications, vol. 17, pp. 1- 14, 2021. https://doi.org/10.1111/10.1145/3408318

[47] Zheng Z., Liu J., Sun D., Lu J., Qiu S., Xiong Y., Liu R., and Cu W., “A Flexible Algorithm Design of Spatial Scalability for Real-Time Surveillance Applications,” The International Arab Journal of Information Technology, vol. 21, no. 6, pp. 1074- 1088, 2024. DOI:10.34028/iajit/21/6/11

[48] Zhu D., Wang Y., You C., Qie J., Cao N., Gong C., Yang G., and Zhao H., “MMLUP: Multi- Source and Multi-Task Learning for User Profiles in Social Network Computer,” Materials and Continuum, vol. 61, no. 3, pp. 1105-1115, 2019. https://doi.org/10.32604/cmc.2019.06041

[49] Zhu H., Zeng H., Liu J., and Zhang X., “Logish: A New Nonlinear Nonmonotonic Activation Function for Convolutional Neural Network,” Neurocomputing, vol. 458, pp. 490-499, 2021. https://doi.org/10.1016/j.neucom.2021.06.067