FORECASTING MOVING AVERAGE PADA DATA TIME SERIES KOTA BANDAR LAMPUNG

Abstract

The current climate change has caused many problems for the surrounding environment. This can be proven by the significant increase in weather temperature, especially in Bandar Lampung City. This study aims to predict weather temperature time series data in Bandar Lampung City using the Forecasting method. This method is combined with the Moving Average technique with three features in the available temperature data, namely Minimum Temperature (Tn), Maximum Temperature (Tx), and Average Temperature (Tavg). Then, the results obtained will be evaluated using the Mean Square Error (MSE) and Root Mean Square Error (RMSE) techniques and compared with existing data. The MSE and RMSE values show relatively small differences, namely 0.74 and 0.86 for Tn, a significant difference of around 0.36 and 0.60 for Tx, while Tavg reached a value of exactly 100. This study requires further experimentation due to the possibility of bias in the data. Therefore, it is recommended to use other methods or add techniques for handling missing values or other techniques so that the results obtained are more accurate and reliable.