TriDeepRec: A Hybrid Deep Learning Approach to Content and Behaviour-based Recommendation Systems
Amirhossein Ghadami, Thomas T. Tran · Research Square · 2024
Abstract Hybrid recommendation systems are increasingly crucial for businesses aiming to boost revenue and customer engagement. These systems integrate various algorithms, each with unique strengths, to outperform traditional recommendation methods. Our study introduces a novel hybrid recommendation system, TriDeepRec, which effectively combines content-based and behaviour-based data to enhance recommendation accuracy. We first introduce a Convolutional Autoencoder-based Recommendation System (CAERS), designed to process content data and extract complex, meaningful patterns, translating these into predictive ratings. Notably, CAERS tackles the cold-start problem by leveraging content information alone, making it robust in scenarios where historical user interaction data is sparse or unavailable. Next, we incorporate Neural Collaborative Filtering (NCF), a deep learning approach, to analyze past user behaviour and predict ratings. The outputs from CAERS and NCF are then integrated using a Multilayer Perceptron (MLP), a type of neural network, to generate the final recommendations. Our methodology employs three deep learning techniques to create TriDeepRec, a system capable of utilizing both past interactions and content attributes. We evaluate our system using two datasets, initially focusing on CAERS to demonstrate its effectiveness in addressing the cold-start problem. Subsequently, we assess the performance of TriDeepRec as a whole. The results, measured in terms of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), indicate significant improvements over both the individual components and other leading models in the field. This demonstrates that TriDeepRec, by 1 harnessing the strengths of both content and behaviour data, provides a more accurate and reliable recommendation system.