APPLICATION OF EXPONENTIAL SMOOTHING METHOD FOR FORECASTING SPARE PARTS INVENTORY AT HEAVY EQUIPMENT DISTRIBUTOR COMPANY.

As a heavy equipment distributor company with a widespread population of units across Indonesia, PT. Kobexindo Tractors Tbk holds a significant spare parts inventory to meet their customers' needs. However, efficiently and effectively managing spare parts inventory is a challenge the company faces. Over the period from 2016 to 2023, the company experienced an average annual loss of Rp. 1,176,438,113, due to the inadequate analysis of spare parts demand, which serves as a reference in the procurement process. To address this issue, this research focuses on developing a model that can generate accurate forecasts for spare parts inventory, particularly Jungheinrich parts, to support appropriate management decisions in the procurement process at the company. The Exponential Smoothing method is chosen for its ability to handle data with fluctuating patterns and trends. Based on a review of previous research studies, the Exponential Smoothing method has proven to be the most effective in forecasting spare parts inventory with a high level of accuracy. This study will compare the Simple Exponential Smoothing, Double Exponential Smoothing, and Triple Exponential Smoothing methods. The attributes included in this research are spare parts inventory data collected from the company during the period of 2016-2023, which will be processed using Exponential Smoothing techniques. The results of these calculations will be evaluated using the Root Mean Square Error (RSME) and Mean Absolute Percentage Error (MAPE) techniques to test the accuracy and performance of the forecasting models. The data ratio used in this research is 70% for training data and 30% for testing data. The prototype development is conducted using the Python programming language. The research results indicate that the Holts Winter Exponential Smoothing Model with Multiplicative Seasonality and Multiplicative Trend (Triple Exponential) is the best method among others, as seen from the modeling evaluation results as follows: 1) Train RSME (7.082307), a low RSME value on training data indicates that this model has a small used for training. 2) Test MAPE (6.343268), a low MAPE value on test data indicates that this model provides fairly accurate predictions in percentage terms of the actual values on the test data. 3) Test RSME Values (23.160521), a sufficiently low RSME value on test data indicates that this model also successfully generalizes well on unseen data.prediction error rate on the data [ABSTRACT FROM AUTHOR]