Product Demand Forecast Analysis Using Predictive Models and Time Series Forecasting Algorithms on the Temu Marketplace Platform

In the rapidly evolving digital era, the ability to accurately forecast product demand is crucial for marketplace platforms like Temu. Demand uncertainty can lead to issues such as overstock or stockout, both of which negatively impact financial performance and customer satisfaction. This study evaluates the use of predictive models and time series forecasting algorithms to forecast product demand on the Temu platform and identifies the latest trends in 2024. Daily sales data were analyzed using various algorithms, including ARIMA, SARIMA, Facebook's Prophet, and LSTM. The analysis results indicate that the Prophet model and SARIMA algorithm provide more accurate predictions compared to ARIMA and LSTM. The proper implementation of predictive models is expected to enhance operational efficiency and support better strategic decision-making for Temu. By adopting the most suitable forecasting models, Temu can optimize inventory management, reduce costs, and improve responsiveness to market changes