OPTIMIZING ARTIFICIAL INTELINGENCE TO PREDICT INDONESIAN GREEN BANKING STOCK

The world is turning green, from waste recycling to wind and solar power generation, which supports the significance of green investments. Everyone is aware of the negative effects of climate change, and the majority of people are very interested in finding solutions. In other words, making green investments may be a good strategy to lessen the environmental burden that humans have caused.
In order to address the aforementioned issues, this project will create a hybrid machine learning system for the Green Banking Stock which included in SRI KEHATI index, an Indonesian green index, using the Long Short Term Memory (LSTM) Method in order to predict the index movement using Phyton programming language.
The study's findings demonstrate that the software's predictions have a tolerable error rate. Median Absolute Error, Mean Absolute Percentage Error, and Median Absolute Percentage Error are the three different error metrics that are utilized.