E-Commerce Inventory Prediction by Hybridization Deep and Machine Learning

Abstract

Inventory management is crucial for the optimisation of consumer demand and supply chains in e-commerce companies. This is the stage at which precise inventory forecasting becomes necessary for the primary objective of forecasting future demand patterns and stock levels. Traditional forecasting methods often struggle with e-commerce data due to seasonality, sudden changes in customer behaviour, and non-linearity. Machine learning (ML) and deep learning (DL) techniques have become powerful weapons for inventory prediction due to their capability of analysing huge amounts of data with high dimensionality. In highly competitive market environments, e-commerce firms can improve their resource allocation, inventory management, and customer experience. This paper proposes different types of inventories forecasting models and especially evaluates the applicability of sophisticated machine learning algorithms. While we commonly use old methods like Random Forest, ARIMA, and MLPs, they often lack the necessary robustness to non-linearity within inventory data. To address these problems, we introduce a novel method that combines convolutional neural networks (CNN) and XGBoost called CNN-XGBoost, which provides better feature extraction than the conventional prediction model and regression performance. We then compared CNN-XGBoost's performance to traditional forecasting methods (another common approach to contextualizing predictive model performance) using a 52-week simulated dataset in which we mimic patient data growing over time.We used key performance metrics such as R2, mean squared error (MSE), and mean absolute percentage error (MAPE) to assess each model's accuracy. The CNN-XGBoost model performed much better than others with an R2 of 0.78, which means our proposed model can explain more variation in comparison to other competitors, as depicted in the results section. It also had the best MSE of 0.15, indicating better predictive performance. The CNN-XGBoost model demonstrated promising prospects as a powerful inventory forecasting tool for commerce, in spite of its slightly higher MAPE value (0.69), suggesting some vulnerability to outlier data points. This study demonstrates the potential of using a convolutional neural network in combination with gradient boosting techniques to tackle the complexity of stock management issues, as well as the fact that it outperforms based line methods by a large margin.