Forecasting with ARIMA and LSTM in Bali Retail Industry

DOI

10.2991/978-94-6463-878-3_22How to use a DOI?

Keywords

ARIMA; Bali Retail Industry; Forecasting; LSTM

Abstract

Food waste significantly contributes to global greenhouse gas emissions, water and air pollution, and socio-economic issues, including in Bali Province. In Bali, increased tourism correlates with population growth and a rise in organic waste, reaching up to 59.10% of total waste. This is largely dominated by imported fruits such as apples, oranges, pears, and grapes, which are also used for religious ceremonies. To mitigate imported fruit waste, limiting imports based on accurate demand forecasting is crucial. Traditional methods like Autoregressive Integrated Moving Average (ARIMA) exhibit limitations in modeling complex non-linear and seasonal patterns, particularly given the fluctuating apple consumption in Bali. Conversely, the Long Short-Term Memory (LSTM) algorithm, a deep learning approach, demonstrates superior capability in capturing linear, non-linear, and dynamic data patterns. This research compares the performance of ARIMA and LSTM models for predicting apple transaction data, evaluating them using the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The aim is to facilitate more precise apple import projections, thereby reducing waste. The results of the research confirmed that the ARIMA method was found to be superior in computational efficiency compared to LSTM, as it required no repeated training iterations. In contrast, LSTM required 25 iterations, making the computation time longer. However, LSTM showed higher accuracy with a MAPE value of 56.58% and RMSE of 28.93, though the difference in RMSE was insignificant compared to ARIMA (28.84), as both algorithms failed to capture the trend of sales spikes during holidays.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Wayan Gede Suka Parwita
AU  - Putu Eka Suryadana
AU  - Gede Sugita Aryandana
PY  - 2025
DA  - 2025/10/31
TI  - Forecasting with ARIMA and LSTM in Bali Retail Industry
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 184
EP  - 192
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_22
DO  - 10.2991/978-94-6463-878-3_22
ID  - Parwita2025
ER  -