Accurate sales forecasting is essential for retail Micro, Small, and Medium Enterprises (MSMEs) to optimize operations and inventory planning in the digital economy. This study compares the forecasting accuracy between Artificial Intelligence (AI)-based methods (Random Forest, Decision Tree) and traditional techniques (Moving Average, Exponential Smoothing) using 3,600 transaction records from five retail MSMEs over three months. A quantitative experimental approach was employed to evaluate model performance under real-world conditions, including market fluctuations and seasonal anomalies. Evaluation metrics include Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and cross-validation techniques. The findings indicate that the Random Forest model achieves superior accuracy (MAPE = 8.5%) compared to traditional methods (MAPE = 15.2%). Explainable AI (XAI) using SHAP and LIME further enhances transparency and managerial trust. Although traditional methods offer faster computation and ease of interpretation, AI-based models show resilience against unpredictable sales patterns. This research recommends hybrid adoption strategies that balance predictive power with interpretability for MSMEs with limited technical capacity. The results contribute to the discourse on digital transformation and intelligent forecasting in the MSME sectors.

The process of accepting new students generates a lot of data in the form of profiles of students who register. From year to year there is an increase in the number of prospective new students who come from several areas in Binjai City, Langkat Regency and surrounding areas, so the location of the socialization of new student admissions promotions every year is increasing and wider. And from several schools that have been visited and are expected to provide new prospective students, in fact, it is not proportional to the final number of prospective students who register. In this study, applying the K-Means Clustering algorithm using 3 variables namely, region, school origin, major. In determining the location of new student admissions promotions, the promotion team first identifies what factors will influence the determination of promotional locations ranging from region, school origin and majors that are considered to be set as promotional locations. Based on the results of grouping new student admission data of STMIK Kaputama Binjai using the K-means Clustering method from 20 data that has been processed, 3 clusters and 3 iterations are produced where cluster 1 has 9 data, cluster 2 has 2 data and cluster 3 has 9 data.

In this study, loading and unloading productivity is influenced by several factors including : handling of the Covid-19 pandemic, operator performance, loading and unloading equipment and stacking field effectiveness. These factors have an important role in increasing loading and unloading productivity. The population in this study were employees of PT. Salam Pacific Indonesia Lines Medan Branch with a total sample of 109 respondents. The data analysis used in this research is descriptive analysis and quantitative analysis, the data is analyzed using multiple linear regression analysis using the Application (SPSS) Version 25. The results of the t-test hypothesis testing indicate that the Covid-19 Pandemic Handling, Operator Performance, Loading and Unloading Equipment and Stacking Field Effectiveness partially positive and significant effect on loading and unloading productivity. Based on the results of the study, it is known that the research model of the multiple linear regression equation resulted in the following equation : Y = 0,329 + 0,177X1 + 0,178X2 + 0,231X3 + 0,380X4 + µ. From the equation results show that the Covid-19 Pandemic Handling variable (X1) has (t count 2,004 > t table 1,983), Operator Performance variable (X2) has (t count 2,085 > t table 1,983), the Unloading Equipment variable (X3) has (t count 2,467 > t table 1,983) and the Stacking Field Effectiveness variable (X4) has (t count 4,243 > t table 1,983). As for the value of Adjusted R2 = 0.604. This means that 60.4% of the variation in the dependent variable (Y), namely the Unloading Productivity is explained by the independent variables, namely the Covid-19 Pandemic Handling (X1), Operator Performance (X2), Loading and Unloading Equipment (X3) and Stacking Field Effectiveness (X4). The remaining 100% - 60.4% = 39.6%, influenced by other variables outside the study.