Design of a consumer behavior prediction model integrating reinforcement learning and time series analysis in online e-commerce reviews
Abstract
This study focuses on the design and optimization of consumer behavior prediction models in online e-commerce reviews. To address the issues of slow convergence and insufficient robustness in the traditional Q-Learning reinforcement learning algorithm, this paper introduces a probabilistic action-selection algorithm. This algorithm employs a multi-step iterative mechanism, utilizing instantaneous differencing to enhance the likelihood of selecting high Q-value actions during model iteration, thereby accelerating the solution process and ensuring the robustness of network optimization. Given the nonlinear and high-noise characteristics of consumer behavior time series data in e-commerce reviews, we propose a hybrid intelligent prediction model, QL-ANN-HMM, which effectively reduces the impact of systematic random errors and significantly improves prediction accuracy. Experimental results demonstrate that the improved Q-learning algorithm achieves a 2.71% and 5.96% improvement in MAPE and NMSE metrics on the Amazon Reviews 2023 and Flipkart Reviews datasets, respectively, compared to the traditional Q-learning algorithm. Additionally, the QL-ANN-HMM model achieves lower MAE, MAPE, and NMSE values on both datasets, recorded at 0.0195, 0.019, and 0.0189, respectively. This research not only provides novel theoretical support and technical methods for predicting consumer behavior in online e-commerce reviews but also enables e-commerce platforms to more accurately track market dynamics, optimize resource allocation, and achieve sustainable development through the comprehensive analysis of consumer behavioral data.