The Strategic Role of Multiple Linear Regression in Forecasting Changes in the Farmer's Exchange Rate

Dhea Hafidzah, Syaharuddin Syaharuddin, Vera Mandailina

Abstract


Abstract: This study aims to analyze and forecast the Farmer Exchange Rate (NTP) in Indonesia using a non-experimental quantitative approach. Secondary data in the form of time series covering the period 2015-2024 were obtained from official sources, such as the Central Statistics Agency (BPS) and Bank Indonesia. In this study, a multiple linear regression model was applied to measure the influence of independent variables, such as inflation, interest rates, global commodity prices, harvest area, and rainfall on NTP. The results of the analysis show that there are fluctuations in the value of NTP, with a general increasing trend, especially after the recovery period after the COVID-19 pandemic. Projections for the period 2025-2029 show a consistent increase in the NTP value, from 132.59 in 2025 to reach 177.82 in 2029. Evaluation of the model using the Mean Squared Error (MSE) indicator of 0.55% and Mean Absolute Percentage Error (MAPE) of 0.4635, which indicates a very good level of prediction accuracy. These findings indicate that the multiple linear regression model is effective in projecting NTP and can be used as a basis in formulating strategic policies for the agricultural sector, especially in improving farmers' welfare through optimization of subsidies, efficient land management, as well as strengthening market access and adoption of modern agricultural technology.

Keywords


Farmer's Exchange Rate, Multiple Linear Regression, Time Series.

Full Text:

PDF

References


Fitriyah, Z., Irsalina, S., K, A. R. H., & Widodo, E. (2021). Analysis of Factors Affecting Ipm Using Multiple Linear Regression. Lebesgue Journal: Scientific Journal of Mathematics Education, Mathematics and Statistics, 2(3), 282-291. https://doi.org/10.46306/lb.v2i3.86

uswadi, J., & Sumarna, P. (2024). The Development of West Java Farmer Exchange Rate (NTP) and its Correlation with Labor, Inflation, and Gross Regional Domestic Product (GRDP) of West Java Agricultural Sector. Paspalum: Scientific Journal of Agriculture, 12(1), 128. https://doi.org/10.35138/paspalum.v12i1.692

Maharadja, A. N., Maulana, I., & Dermawan, B. A. (2021). Application of Multiple Linear Regression Method for Prediction of State Losses Based on Corruption Crime Cases. Journal of Applied Informatics and Computing, 5(1), 95-102. https://doi.org/10.30871/jaic.v5i1.3184

Mona, M., Kekenusa, J., & Prang, J. (2015). Use of Multiple Linear Regression to Analyze Coconut Farmers' Income. Case Study: Coconut Farmers in Beo Village, Beo District, Talaud Regency. D'CARTESIAN, 4(2), 196. https://doi.org/10.35799/dc.4.2.2015.9211

Nurani, A. T., Setiawan, A., & Susanto, B. (2023). Performance Comparison of Decision Tree Regression and Multiple Linear Regression for BMI Prediction on Asthma Dataset. Journal of Science and Science Education, 6(1), 34-43. https://doi.org/10.24246/juses.v6i1p34-43

Panggabean, D. S. O., Buulolo, E., & Silalahi, N. (2020). Application of Data Mining to Predict Tree Seedling Orders with Multiple Linear Regression. JURIKOM (Journal of Computer Research), 7(1), 56. https://doi.org/10.30865/jurikom.v7i1.1947

Prasetyo, R. A. (2022). Multiple Linear Regression Analysis to Look at Factors Affecting Poverty in West Sumatra Province. Journal of Mathematics UNP, 7(2), 62. https://doi.org/10.24036/unpjomath.v7i2.12777

Sarumpaet, I., & Hermanto, B. (2025). Factors Affecting Income (Case Study: In Kedai Tiga Village, Barus District). AgroNusantara Journal, 5.

Susanti, I., & Saumi, F. (2022). Application of Multiple Linear Regression Analysis Method to Overcome Multicollinearity Problem in the Case of Human Development Index (Ipm) in Aceh Tamiang Regency. Gamma-Pi: Journal of Mathematics and Applied, 4(2), 38-42.


Refbacks

  • There are currently no refbacks.