Have a personal or library account? Click to login

A Supervised Machine Learning in Financial Forecasting: Identifying Effective Models for the BIST100 Index

Review of Economic Perspectives
Volume 25 (2025): Issue 1 (March 2025)
By:
Open Access
|Sep 2025

Figures & Tables

Fig. 1:

Data Preprocessing for Machine Learning
Data Preprocessing for Machine Learning

Fig. 2:

Experimental design of study
Experimental design of study

Fig. 3:

Tree-based models fitting results. Each subplot shows the predicted vs. actual closing prices for a specific Tree-Based Model (Decision Trees, Bagging, Random Forests, AdaBoost, GBM, LightGBM, XGBoost, CatBoost) applied to the BIST100 dataset. The blue line represents the actual closing prices, while the orange line represents the model’s predicted values. Closer alignment between the lines indicates higher predictive accuracy.
Tree-based models fitting results. Each subplot shows the predicted vs. actual closing prices for a specific Tree-Based Model (Decision Trees, Bagging, Random Forests, AdaBoost, GBM, LightGBM, XGBoost, CatBoost) applied to the BIST100 dataset. The blue line represents the actual closing prices, while the orange line represents the model’s predicted values. Closer alignment between the lines indicates higher predictive accuracy.

Fig. 4:

Neural Network-Based Models fitting results. This figure illustrates the predicted vs. actual financial performance for Neural Network-Based Models (ANN, CNN, RNN, LSTM) using the BIST100 dataset. Lower deviation from the diagonal line indicates better predictive accuracy.
Neural Network-Based Models fitting results. This figure illustrates the predicted vs. actual financial performance for Neural Network-Based Models (ANN, CNN, RNN, LSTM) using the BIST100 dataset. Lower deviation from the diagonal line indicates better predictive accuracy.

Fig. 5:

Instance-based Learning Models fitting results. This figure compares the predicted vs. actual financial performance for Instance-Based Learning Models (KNN, SVM) on the BIST100 dataset. Performance differences are reflected in the proximity of predictions to the actual values.
Instance-based Learning Models fitting results. This figure compares the predicted vs. actual financial performance for Instance-Based Learning Models (KNN, SVM) on the BIST100 dataset. Performance differences are reflected in the proximity of predictions to the actual values.

MSE, RMSE, MAE, MAPE and rRMSE values

 MSERMSEMAEMAPErRMSE
Decision Trees3.258e–050.00570.00322.45910.0283
Bagging1.671e–050.00410.00262.18760.0202
Random Forests1.635e–050.00410.00241.95410.0201
Adaboost2.272e–050.00470.00252.01660.0236
GBM2.035e–050.00450.00231.65850.0223
LightGBM2.739e–050.00520.00261.75100.0259
XGBoost2.662e–050.00510.00251.76880.0256
CatBoost3.129e–050.00550.00373.00350.0277
ANN0.000420.02050.015113.66400.1019
CNNs2.886e–050.00530.00394.18930.0266
RNNs6.565e–050.00810.00605.60110.0402
LSTMs0.00010.01060.00787.31470.0528
KNN0.00010.01010.00717.05580.0501
SVM1.592e–050.00390.00313.51480.0198

Characteristics of the dataset

VariableDescription
DateDate of observation
OpenOpening price on the given day
HighHighest price on the given day
LowLowest price on the given day
CloseClosing price on the given day
Simple Moving Average (SMA)Average of closing prices over a specified period
Weighted Moving Average (WMA)Average of closing prices over a specified period, weighted by recent prices
Momentum (MOM)Rate of change of the closing price over a specified period
Stochastic %K (STCK)Current closing price relative to the range over a recent period
Stochastic %D (STCD)Moving average of the Stochastic %K
Relative Strength Index (RSI)Measures the magnitude of recent price changes to evaluate overbought or oversold conditions
Moving Average Convergence Divergence (MACD)Difference between the 12-day and 26-day exponential moving averages (EMAs)
Larry William’s %R (LWR)Momentum indicator measuring overbought and oversold levels
Accumulation/Distribution Oscillator (ADO)Indicator combining price and volume to show how much of a stock is being accumulated or distributed
Commodity Channel Index (CCI)Measures the deviation of the price from its average over a specified period, indicating overbought or oversold conditions
DOI: https://doi.org/10.2478/revecp-2025-0005 | Journal eISSN: 1804-1663 | Journal ISSN: 1213-2446
Journal RSS Feed
Language: English
Page range: 66 - 90
Published on: Sep 8, 2025
Published by: Mendel University in Brno
In partnership with: Paradigm Publishing Services
Publication frequency: 2 times per year
Keywords:
tree-based models,
neural network-based models,
instance-based learning models
Related subjects:
Business and economics,
Political economics,
Economic theory, systems and structures

© 2025 Cansu Ergenç, Rafet Aktaş, published by Mendel University in Brno
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 25 (2025): Issue 1 (March 2025)