Intern(Chow Jun Hoe)

 19/9/2025 Today's main task is to complete the handover work, including returning the company-issued computer and backpack, and confirming that the relevant information and documents have been properly organized.

 18/9/2025 My main task today is to compile a tool library to systematically document what I've learned during my six-month internship. This library covers common data filtering and cleaning methods in Python, modeling scripts for time series forecasting (such as Holt-Winters, ARIMA/SARIMA, XGBoost, and N-BEATS), and techniques used in feature engineering. I've also organized common Excel functions and formulas into notes for quick reference. This compilation will not only help me solve similar problems more efficiently in the future, but also provide a resource for the team to reference and reuse.

 17/9/2025 Today's main task is to report the previously improved summary to the manager again, and make final revisions and improvements based on the feedback to ensure that the content is complete and the expression is clear so that it can be used as the final version.

 16/9/2025 Public Holiday

15/9/2025  Public Holiday

 12/9/2025 Today's main task is to review the ARIMA and SARIMA scripts I wrote previously, looking for areas for improvement in parameter selection, data preprocessing, and seasonality settings, in order to improve forecast accuracy and stability. However, ARIMA and SARIMA are more suitable for short-term forecasts because, when the forecast timeframe is too long, errors gradually accumulate, resulting in significant deviations in the results.

 11/9/2025 My main task today was to systematically organize and record the Excel and Python functions and methods I'd learned during my internship, so I could quickly review them later. In this process, I not only categorized common functions (such as VLOOKUP, IF, INDEX MATCH, SUMIF, TEXT, etc.) by function, but also wrote down application scenarios and sample code based on previous examples of actual data manipulation.

 10/9/2025 Today, I reviewed the data filtering methods I used in Python during my internship. By reviewing common Pandas syntax, such as loc and isin, and combining conditional filtering, I gained a clearer understanding of how to quickly extract the required data based on different conditions.

 9/9/2025 Today, I started applying the Excel functions I learned yesterday to real-world data processing, operating and validating real sales and inventory data. For example, I used VLOOKUP and INDEX MATCH to match information from different tables.

 8/9/2025 Today, I continued to revise and optimize the summary, focusing on improving the explanation of the data analysis methods to make the overall content clearer. After completing the revisions, I began to learn how to use Excel functions, including common formulas such as VLOOKUP, INDEX, MATCH, and IF. I also tried to apply these functions to daily data analysis to improve the efficiency of data processing and filtering.

 5/9/2025 Public Holiday

 4/9/2025 Today, I presented the content I prepared the day before to the team. I detailed the process of building the predictive model, its performance in different scenarios, and its limitations. During the presentation, the manager offered suggestions for improvements to some of the data processing methods and feature design.

 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.

 2/9/2025 My main task today was to complete and refine the presentation for tomorrow's presentation, ensuring that all slides were logically clear, data accurate, and case studies complete. I reviewed and fine-tuned each model's prediction results and their strengths and weaknesses, optimizing the presentation order and chart layout to more intuitively showcase the analysis results and learnings from my internship.

 1/9/2025 Public Holiday