In handling large-scale user and item data, recommendation systems often face the challenge of information overload, making the improvement of recommendation accuracy and efficiency a critical research direction. In recent years, recommendation algorithms based on deep learning have increasingly dominated the field, with feedforward neural networks gaining widespread application due to their flexibility and scalability. However, the high sparsity of user-item data presents a key challenge in effectively leveraging these sparse features to enhance model performance. This study utilizes the Movielens movie dataset and generates sparse features through feature engineering, proposing a multilayer perceptron model based on sparse features. The model is compared with classical models such as logistic regression, random forest, and gradient boosting decision trees (GBDT). Experimental results demonstrate that the feedforward neural network based on sparse features exhibits significant advantages in performance metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Area Under the Curve (AUC). This study provides both theoretical foundations and practical guidance for optimizing recommendation systems in sparse data environments, with important application value.

Guo Jiajie. Improving Movie Recommendations Using Multilayer Perceptron Model and Sparse Feature Integration. The Frontiers of Society, Science and Technology (2024), Vol. 6, Issue 9: 35-40. https://doi.org/10.25236/FSST.2024.060906.

[1] Wang G, Zhao J, Li X, et al. Weighted Granular Sequence Recommendation Algorithm Based on Content[J]. Computer Science, 2020, 47(3): 72-78.

[2] Jin X, Zhang Y, Wang H, et al. Research on Movie Recommendation System Based on Deep Learning[J]. Computer Engineering and Applications, 2019, 55(18): 235-240.

[3] Wang Y, Liu M, Zhao L, et al. An Efficient SVD++ Algorithm with Improved Learning Rate[J]. Modern Computers, 2021, 47(3): 56-63.

[4] Zhao G S, Zhang H, Wang X, et al. Design of a Movie Recommendation System Based on IRGAN Model and Hadoop[J]. Computer Engineering, 2020, 46(9): 67-71.

[5] Gu Y R, Zhang J, Li H, et al. Movie Recommendation Algorithm Based on Movie Attributes and Interaction Information[J]. Computer Applications, 2021, 41(11): 302-308.

[6] Zhang Y L, Wang Z, Liu Y, et al. Research on KNN Classification Recommendation Algorithm Based on Dynamic User Portrait Tags[J]. Journal of Software, 2020, 31(9): 2762-2770.

[7] Jin S S, Chang H Z, et al. Design of a Film and Television Recommendation System Based on Multidimensional Data Fusion[J]. Modern Electronics Technology, 2023, 45(17): 123-128.

[8] Wang M S, Chen X, Zhao L, et al. Long-Term Recommendation Based on Bipartite Networks[J]. Software Guide, 2020, 19(7): 34-40.

[9] Hu X L, Li Z, Wang M, et al. A Review of Recommendation Algorithms Based on Distributed Representation Technology[J]. Application Research of Computers, 2018, 35(12): 3789-3793.

[10] He J, Wang Z, Liu Y, et al. Multimodal Information Processing Methods and Their Applications Based on Convolutional Neural Networks[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(1): 85-91.

[11] Liu H L, Zhang J, Wang Q, et al. A Survey of Content Recommendation Algorithms Based on Deep Learning[J]. Computer Engineering and Applications, 2019, 55(14): 120-126.

[12] Chen N, Wu J B, et al. Multi-Criteria Decision Recommendation System Based on Neural Networks[J]. Control Engineering, 2018, 25(5): 841-848.

[13] Liu X W, Li S, Zhao H, et al. Personalized Movie Recommendation System Based on Collaborative Filtering[J]. Computer Science, 2019, 46(5): 50-55.

[14] Li K L, Zhao L, Wang H, et al. Recommendation Algorithm Based on Attention Mechanism and Improved TF-IDF[J]. Computer Engineering, 2019, 45(6): 56-60.

[15] Tan T Z, Zhang J, et al. Hybrid Recommendation System Based on Attention Model[J]. Computer Engineering and Applications, 2020, 56(13): 37-42.

[16] Zhong Z F, Zhou D P, Zhang Y, et al. Research on Hybrid Recommendation Model Based on Least Squares Method[J]. Modern Electronics Technology, 2022, 45(17): 123-128.

[17] He M, Zhao L, Li X, et al. Collaborative Filtering Recommendation Algorithm Integrating Category Information and User Interest[J]. Computer Science and Exploration, 2020, 14(8): 1257-1264.

[18] Li M H, Zhang H, et al. Progress in Recommendation Algorithms[J]. Computer Engineering and Design, 2018, 39(3): 832-839.

[19] Huang B, Liu J, et al. Progress and Applications of Recommendation Systems[J]. Application Research of Computers, 2019, 36(11): 3417-3423.

[20] Zhang F G, Li W, et al. A Recommendation Algorithm Based on Criterion-Level Feature Cross-Fusion[J]. Computer Science, 2020, 47(5): 83-89.