<![CDATA[Unemployment remains a key socio-economic indicator that reflects both economic performance and human development conditions at the regional level. In North Sulawesi Province, unemployment levels have shown noticeable fluctuations over the past two decades, driven by changes in labour market structure, workforce characteristics, and development outcomes. This study aims to forecast the number of unemployed people in North Sulawesi by applying a multivariate Long Short-Term Memory model capable of capturing long-term temporal dependencies in time-series data. The analysis uses annual data published by Statistics Indonesia for the period 2000–2025. Several explanatory variables are selected through Pearson correlation analysis, including the Open Unemployment Rate, the number of unemployed women, the population that has never been employed, and the Human Development Index. All variables are normalised and transformed into five-year sliding windows to preserve temporal relationships. The model is constructed using a single hidden layer with 32 units and a dropout rate of 0.2 and is trained using the Adam optimisation algorithm. The evaluation results indicate that the proposed model achieves satisfactory predictive accuracy, with a Mean Absolute Error of 2,960 persons, a Root Mean Square Error of 3,454 persons, and a Mean Absolute Percentage Error of 3.56 percent. Forecasting results for the 2026–2030 period show a gradual decline in unemployment levels. These findings suggest that the model provides reliable unemployment projections and supports data-driven employment policy planning in North Sulawesi.]]>
Copyrights © 2026
