3/9/2025

 3/9/2025

Today, I continued my in-depth study of the principles and structure of the N-BEATS model, including its time series forecasting mechanism based on a feedforward neural network, its trend and seasonality decomposition methods, and its strengths and limitations in long-term forecasting. Integrating this with EcoShop's sales data, I began to consider how, building on existing feature engineering, N-BEATS could be applied to forecasting scenarios involving special factors such as holidays and price fluctuations.

评论

发表评论

此博客中的热门博文

10/6/2025

 10/6/2025 Today, i successfully completed the construction of the SARIMA model and began to apply it to the prediction of actual sales data. After model training, i generated sales forecasts for the next few days and compared them with the actual data to evaluate the accuracy of the model.
阅读全文

22/5/2025

 22/5/2025 Continue to modify the analysis content based on the feedback from Supply Chain Executive, including optimizing the data display format, supplementing missing data fields, and reorganizing the analysis logic. While completing the modifications, also start preparing for the report to be given tomorrow and organize the required forecast model results.
阅读全文