Evaluation of the Implementation of Main Distribution Material (MDU) Spare Part Procurement at Seven Customer Service Units (ULP) in Semarang Area using ABC Analysis and Time Series Forecasting (Case Study: PT PLN (Persero) UP3 Semarang) Time series forecasting is a method used to predict the number of future needs in a time series. This research was conducted at the company PT PLN (Persero) UP3 Semarang, where the author tried to deal with the company's problems related to the procurement of Main Distribution Material (MDU) which often occurs overstock or lack of stock. The author uses ABC analysis to classify goods based on value ratings ranging from the highest value so that three parts with group A are obtained for forecasting, kWH meters, 2 × 10 mm2 PWR cables, and 4A MCBs. Forecasting is done with four methods, the Multiplicative Decomposition method, the Holt-Winters method, the Moving Average method, and the Exponential Smoothing method. From the results of the error calculation, it is obtained that the Holt-Winters method obtains the lowest percentage error with results of 10% - 20% or is good to use for forecasting. The comparison between the forecasting results and the overall actual demand is above 70%, which means that the forecasting results are close to the actual demand that occurs, thus increasing the accuracy of the Holt-Winters forecasting method. Suggestions for improvement that can be given to the company are to apply the Holt-Winters forecasting method in forecasting MDU spare part inventory at PT PLN (Persero) UP3 Semarang.
Read full abstract