Using Stacked Generalization Model in Stock Price Forecasting: A Comparative Analysis on BIST100 Index

Ahmed İhsan Şimşek

Makale detayları

Using Stacked Generalization Model in Stock Price Forecasting: A Comparative Analysis on BIST100 Index

Yazarlar:

Ahmed İhsan Şimşek

Yayıncı:

Ahmet Arif EREN

Ana Başlıklar:

Zaman Serileri Analizi

Dergi:

Fiscaoeconomia Vol.9 Issue 1, pp.305-322

Belge Tipi:

Makale

Yayın Tarihi:

2/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001341603

pISSN:

2564-7504

Anahtar kelimeler:

Özet:

 Investing in financial markets requires an adequately planned approach and decision-making process for both individual and institutional investors. The volatility of financial markets is influenced by intricate and constantly evolving factors, prompting investors, analysts, and financial experts to employ progressively sophisticated and data-centric methodologies to precisely forecast future price swings. Deep learning models for stock price prediction demonstrate the ability to comprehend intricate connections by amalgamating extensive datasets. The objective of this essay is to employ various machine learning models using daily data from the BIST100 index, a prominent financial indicator in Turkey. The models under question encompass Support Vector Regression SVR, K-Nearest Neighbors KNN, Random Forest RF, XGBoost and Stacked Generalization. The models prediction skills were evaluated using RMSE, MSE, MAE, and R2 performance indicators. Based on the observed results, the Stacked Generalization model demonstrated greater performance in making predictions for the analyzed dataset. These findings offer valuable insights that should be considered when selecting models for similar analyses in the future.

 Investing in financial markets requires an adequately planned approach and decision-making process for both individual and institutional investors. The volatility of financial markets is influenced by intricate and constantly evolving factors, prompting investors, analysts, and financial experts to employ progressively sophisticated and data-centric methodologies to precisely forecast future price swings. Deep learning models for stock price prediction demonstrate the ability to comprehend intricate connections by amalgamating extensive datasets. The objective of this essay is to employ various machine learning models using daily data from the BIST100 index, a prominent financial indicator in Turkey. The models under question encompass Support Vector Regression SVR, K-Nearest Neighbors KNN, Random Forest RF, XGBoost and Stacked Generalization. The models prediction skills were evaluated using RMSE, MSE, MAE, and R2 performance indicators. Based on the observed results, the Stacked Generalization model demonstrated greater performance in making predictions for the analyzed dataset. These findings offer valuable insights that should be considered when selecting models for similar analyses in the future.

 Investing in financial markets requires an adequately planned approach and decision-making process for both individual and institutional investors. The volatility of financial markets is influenced by intricate and constantly evolving factors, prompting investors, analysts, and financial experts to employ progressively sophisticated and data-centric methodologies to precisely forecast future price swings. Deep learning models for stock price prediction demonstrate the ability to comprehend intricate connections by amalgamating extensive datasets. The objective of this essay is to employ various machine learning models using daily data from the BIST100 index, a prominent financial indicator in Turkey. The models under question encompass Support Vector Regression SVR, K-Nearest Neighbors KNN, Random Forest RF, XGBoost and Stacked Generalization. The models prediction skills were evaluated using RMSE, MSE, MAE, and R2 performance indicators. Based on the observed results, the Stacked Generalization model demonstrated greater performance in making predictions for the analyzed dataset. These findings offer valuable insights that should be considered when selecting models for similar analyses in the future.

 Finansal piyasalara yatırım yapmak hem bireysel hem de kurumsal yatırımcılar için önemli bir strateji ve karar alma sürecini gerektirmektedir. Finansal piyasaların oynaklığı, karmaşık ve sürekli gelişen faktörlerden etkilenerek yatırımcıları, analistleri ve finansal uzmanları gelecekteki fiyat dalgalanmalarını kesin olarak tahmin etmek için giderek daha karmaşık ve veri merkezli metodolojiler kullanmaya teşvik etmektedir. Hisse senedi fiyat tahmini için derin öğrenme modelleri, kapsamlı veri kümelerini birleştirerek karmaşık bağlantıları kavrama yeteneği sayesinde giderek daha çok tercih edilmektedir. Bu makalenin amacı, Türkiyenin önemli finansal göstergelerinden biri olan BIST100 endeksine ait 04.01.2010-29.11.2023 tarihleri arasındaki 3494 günlük veri setini kullanarak en iyi tahmin yeteneğine sahip modeli belirlemektir. Bu kapsamda SVR, KNN, RF, XGBoost ve Stacked Generalization modeli kullanılmıştır. Modellerin tahmin becerileri RMSE, MSE, MAE ve R2 performans göstergeleri kullanılarak değerlendirilmiştir. Modellerin tahmin performanslarından elde edilen sonuçlara göre, Stacked generalization modeli analiz edilen veri kümesi için tahminler yapmada daha yüksek performans göstermiştir. Bu bulgular gelecekte benzer analizler için model seçerken dikkate alınması gereken değerli bilgiler sunmaktadır.

Makale detayları

Using Stacked Generalization Model in Stock Price Forecasting: A Comparative Analysis on BIST100 Index

Yazarlar:

Ahmed İhsan Şimşek

Yayıncı:

Ahmet Arif EREN

Ana Başlıklar:

Zaman Serileri Analizi

Dergi:

Fiscaoeconomia Vol.9 Issue 1, pp.305-322

Belge Tipi:

Makale

Yayın Tarihi:

2/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001341603

pISSN:

2564-7504

BIST100

Stacked Generalization

Stock Prediction

Decision Support

Time SeriesBIST100

Stacked Generalization

Hisse Senedi Tahmini

Karar Destek

Zaman Serisi

Sayı

Makale detayları

Yazarlar: Ahmed İhsan Şimşek

Yayıncı: Ahmet Arif EREN

Ana Başlıklar: Zaman Serileri Analizi

Dergi: Fiscaoeconomia Vol.9 Issue 1, pp.305-322

Belge Tipi: Makale

Yayın Tarihi: 2/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001341603

pISSN: 2564-7504

Sayı

Yazarlar:

Ahmed İhsan Şimşek

Yayıncı:

Ahmet Arif EREN

Ana Başlıklar:

Zaman Serileri Analizi

Dergi:

Fiscaoeconomia Vol.9 Issue 1, pp.305-322

Belge Tipi:

Makale

Yayın Tarihi:

2/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001341603

pISSN:

2564-7504