JKII Stock Price Prediction
Jakarta Islamic Index price forecasting with LSTM, XGBoost, SVR and more — evaluated on 5 metrics, deployed on Streamlit.
Architecture
Time-series forecasting: JKII prices through feature prep, five models, multi-metric evaluation, and a Streamlit app.
Overview
My undergraduate final project: forecasting the close price of the Jakarta Islamic Index (JKII) using Yahoo Finance data.
I compared five approaches — LSTM, XGBoost, Linear Regression, Gradient Boosting, and SVR — and evaluated them across five metrics including MAPE, MSE, RMSE, and Huber loss. The final model was deployed as a Streamlit app.
Highlights
- 5 models: LSTM, XGBoost, Linear Regression, Gradient Boosting, SVR
- Evaluated on 5 metrics (MAPE, MSE, RMSE, Huber loss, …)
- Deployed with Streamlit
Context
Undergraduate final project
Tech stack
More projects
View all →Rice Leaf Disease Classification (CNN)
CNN image classification of rice leaf diseases with a custom model plus AlexNet, VGG19, and DenseNet — deployed on Flask.
SMILE Platform (UNDP for Kemenkes)
National immunization logistics system in production across all of Indonesia — streaming CDC + batch analytics platform.
LidValid — Unified Data Validation Platform
Full-stack data validation platform with Tiered Validation — cheap aggregate checks across every table, then precise row-level checks only where they fail.