25/7/2025

 25/7/2025

Today's model adjustment work has achieved interim results. Through carefully designed holiday-related variables, I successfully made the XGBoost model's prediction trend during Hari Raya closer to the actual sales data. Not only did it show a significant expected increase before the festival, but it also correctly captured the peak during the festival and the decline after the festival. The overall accuracy (such as MAPE) has also improved. However, when further observing the model's prediction performance at other key points (such as after the product price increase), it was found that the model's perception of "sales volume changes after the price increase" is insufficient. Further adjustments are needed.

评论

发表评论

此博客中的热门博文

21/3/2025

 21/3/2025 Continue to explore and test various sales forecasting methods, including using different time periods for forecasting, to find the most accurate forecasting method. Attend meetings in the afternoon to discuss inventory status during the promotion period with relevant teams (such as managers and executives), focusing on products that have already started or are about to start promotions, especially products that are at risk of being out of stock (OOS), and develop corresponding response strategies to ensure the smooth progress of promotions.
阅读全文

19/3/2025

19/3/2025 Data related to Soh (Stock on hand), Sales (Sales data) and Warehouse Stock (Warehouse Stock) from January 2, 2025 to March 19, 2025 are extracted from Qlik Sense, and the data integrity is checked and initially cleaned. Subsequently, the stock level and warehouse stock allocation are analyzed by building visualization charts such as line charts and bar charts. Finally, the analysis results are discussed and corrected with the Supply Chain Forecast and Promotion Executive.
阅读全文