Jakarta Composite Index Model Before and During COVID-19 Using CNN-LSTM

DOI

10.2991/aer.k.211222.036How to use a DOI?

Keywords

Deep Learning; CNN-LSTM; JCI; COVID-19

Abstract

Deep Learning is a subset of artificial intelligence and machine learning, which is the development of multiple layered neural networks. There are many sectors that deep learning can be applied to such as computer vision, natural languages processing, and even time series data forecasting. One of the deep learning algorithms that have depth in forecasting time series data is CNN-LSTM. CNN-LSTM (Convolutional Neural Network - Long Sort Term Memory) is a deep learning algorithm that uses a convolution layer to automate data extraction and an LSTM layer to learn data patterns by paying attention to the order in the data. In this study, CNN-LSTM was used to model the JCI (Jakarta Composite Index) before the COVID-19 period and during the COVID-19 period. JCI data was taken from December 1, 2018 to June 1, 2021. JCI data was split into data training, data validation, and data testing. Based on the analysis, the MAPE value was 1.4% for the JCI test data before COVID-19 and 0.5% for the JCI test data during COVID-19. From the MAPE value, it can be said that CNN-LSTM has excellent forecasting capabilities for JCI data before and during COVID-19.

Copyright

© 2021 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Yogi Anggara
AU  - Epha Diana Supandi
PY  - 2021
DA  - 2021/12/23
TI  - Jakarta Composite Index Model Before and During COVID-19 Using CNN-LSTM
BT  - Proceedings of the International Conference on Science and Engineering (ICSE-UIN-SUKA 2021)
PB  - Atlantis Press
SP  - 226
EP  - 232
SN  - 2352-5401
UR  - https://doi.org/10.2991/aer.k.211222.036
DO  - 10.2991/aer.k.211222.036
ID  - Anggara2021
ER  -