PERFORMANCE EVALUATION OF THE INDF.JK STOCK PRICE MOVEMENT PREDICTION MODEL USING RANDOM FOREST METHOD WITH GRID SEARCH CROSS VALIDATION OPTIMIZATION

Investment in financial instruments in Indonesia has shown significant growth over time, with stocks often being the first choice for investors to invest money. Unfortunately, deciding to buy and sell stocks is not easy. When determining the right time to buy or sell stocks, volatile stock price movements and losses caused by wrong decisions are investors' problems. Thus, it is essential to analyze stock price movement predictions. This study aims to evaluate the prediction model's performance for PT Indofood Sukses Makmur Tbk (INDF.JK) stock price movement in the next 30 days to reduce the risk of possible losses and help the decision-making process. We used the Random Forest method and Grid Search Cross Validation (CV) optimization to form the model. The data used is the closing price of INDF.JK stock for the period January 2, 2014, to December 29, 2023, from Yahoo Finance, which is processed into eight types of stock technical indicators, namely SMA_5, SMA_10, SMA_15, SMA_30, EMA_9, MACD, MACD_Signal, and RSI. The research pipeline includes descriptive statistics, preprocessing, feature and target variables determination, data split, model formation without and with optimization, testing accompanied by performance evaluation, and comparison of the formed model. The results show that the prediction model of INDF. JK's stock price movement in the next 30 days has excellent performance, proven accurate by 90.8% with the application of Random Forest and Grid Search CV. The Random Forest prediction model with Grid Search CV optimization has better performance indicators than the Random Forest model without Grid Search CV optimization, which is shown by the increase of all indicator values. The relative Strength Index is the variable with the best performance for the prediction model. It can be used as the primary consideration for investors when deciding on the buying and selling process of INDF.JK stock in the next 30 days.

Authors

Institutions

Publication Details

Journal
BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN
Published
2025-07-01
DOI
https://doi.org/10.30598/barekengvol19iss3pp2155-2168
Primary Topic
Stock Market Forecasting Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

PERFORMANCE EVALUATION OF THE INDF.JK STOCK PRICE MOVEMENT PREDICTION MODEL USING RANDOM FOREST METHOD WITH GRID SEARCH CROSS VALIDATION OPTIMIZATION

Shantika Martha, Evy Sulistianingsih, Wirda Andani, Della Zaria
BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN
Stock Market Forecasting Methods
article

PERFORMANCE EVALUATION OF THE INDF.JK STOCK PRICE MOVEMENT PREDICTION MODEL USING RANDOM FOREST METHOD WITH GRID SEARCH CROSS VALIDATION OPTIMIZATION

Shantika Martha, Evy Sulistianingsih, Wirda Andani, Della Zaria
article en

Abstract

Investment in financial instruments in Indonesia has shown significant growth over time, with stocks often being the first choice for investors to invest money. Unfortunately, deciding to buy and sell stocks is not easy. When determining the right time to buy or sell stocks, volatile stock price movements and losses caused by wrong decisions are investors' problems. Thus, it is essential to analyze stock price movement predictions. This study aims to evaluate the prediction model's performance for PT Indofood Sukses Makmur Tbk (INDF.JK) stock price movement in the next 30 days to reduce the risk of possible losses and help the decision-making process. We used the Random Forest method and Grid Search Cross Validation (CV) optimization to form the model. The data used is the closing price of INDF.JK stock for the period January 2, 2014, to December 29, 2023, from Yahoo Finance, which is processed into eight types of stock technical indicators, namely SMA_5, SMA_10, SMA_15, SMA_30, EMA_9, MACD, MACD_Signal, and RSI. The research pipeline includes descriptive statistics, preprocessing, feature and target variables determination, data split, model formation without and with optimization, testing accompanied by performance evaluation, and comparison of the formed model. The results show that the prediction model of INDF. JK's stock price movement in the next 30 days has excellent performance, proven accurate by 90.8% with the application of Random Forest and Grid Search CV. The Random Forest prediction model with Grid Search CV optimization has better performance indicators than the Random Forest model without Grid Search CV optimization, which is shown by the increase of all indicator values. The relative Strength Index is the variable with the best performance for the prediction model. It can be used as the primary consideration for investors when deciding on the buying and selling process of INDF.JK stock in the next 30 days.

BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPANVol. 19(3)
Tanjungpura University (ID)
Openalex Percentile: Top 81%
Stock Market Forecasting Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.