Published July 1, 2019 | Version v1
Publication Open

AN ANALYSIS ON INVESTMENT PERFORMANCE OF MACHINE LEARNING: AN EMPIRICAL EXAMINATION ON TAIWAN STOCK MARKET

Creators

  • 1. Ling Tung University
  • 2. University of Science and Technology
  • 3. National Yunlin University of Science and Technology
  • 4. National Taichung University of Science and Technology

Description

This study aims to explore the prediction of Taiwan stock price movement and conduct an analysis of its investment performance. Based on Taiwan Stock Market index, the study compares four machine learning models: ANN, SVM, Random Forest and Naïve-Bayes. With a performance evaluation of Taiwan Stock Market index historical data spanning from 2014 to 2018, we find: (1) By overall performance measures, machine learning models outperform benchmark market index. (2) By risk-adjusted measures, the empirical results suggest that ANN generates the best performance, followed by SVM and Random Forest, and Naïve-Bayes coming in last.Keywords: Naive-Bayes, ANN, SVM, Random Forest, Machine Learning, Investment PerformanceJEL Classifications: C11; C53; C63; G11DOI: https://doi.org/10.32479/ijefi.8129

⚠️ This is an automatic machine translation with an accuracy of 90-95%

Translated Description (Arabic)

تهدف هذه الدراسة إلى استكشاف التنبؤ بحركة سعر سهم تايوان وإجراء تحليل لأدائها الاستثماري. استنادًا إلى مؤشر سوق الأسهم التايواني، تقارن الدراسة أربعة نماذج للتعلم الآلي: ANN و SVM و Random Forest و Naöve - Bayes. من خلال تقييم أداء البيانات التاريخية لمؤشر سوق الأسهم التايواني التي تمتد من عام 2014 إلى عام 2018، نجد: (1) من خلال مقاييس الأداء الإجمالية، تتفوق نماذج التعلم الآلي على مؤشر السوق القياسي. (2) من خلال المقاييس المعدلة حسب المخاطر، تشير النتائج التجريبية إلى أن ANN تحقق أفضل أداء، تليها SVM و Random Forest، و Naéve -Bayes في المرتبة الأخيرة. الكلمات الرئيسية: السذاجة-Bayes، ANN، SVM، Random Forest، التعلم الآلي، الأداء الاستثماري تصنيفات JEL: C11 ؛ C53 ؛ C63 ؛ G11DOI: https://doi.org/10.32479/ijefi.8129

Translated Description (English)

This study aims to explore the prediction of Taiwan stock price movement and conduct an analysis of its investment performance. Based on Taiwan Stock Market index, the study compares four machine learning models: ANN, SVM, Random Forest and Naà ¶ ve-Bayes. With a performance evaluation of Taiwan Stock Market index historical data spanning from 2014 to 2018, we find: (1) By overall performance measures, machine learning models outperform benchmark market index. (2) By risk-adjusted measures, the empirical results suggest that ANN generates the best performance, followed by SVM and Random Forest, and Naà ¶ ve -Bayes coming in last.Keywords: Naive-Bayes, ANN, SVM, Random Forest, Machine Learning, Investment PerformanceJEL Classifications: C11; C53; C63; G11DOI: https://doi.org/10.32479/ijefi.8129

Translated Description (French)

Cette étude vise à explorer la prédiction de l'évolution du cours des actions taïwanaises et à effectuer une analyse de sa performance d'investissement. Sur la base de l'indice boursier de Taiwan, l'étude compare quatre modèles d'apprentissage automatique : ANN, SVM, Random Forest et Naà ¶ ve-Bayes. Avec une évaluation de la performance des données historiques de l'indice boursier de Taiwan couvrant la période 2014 à 2018, nous trouvons : (1) Par des mesures de performance globale, les modèles d'apprentissage automatique surperforment l'indice de marché de référence. (2) Par des mesures ajustées au risque, les résultats empiriques suggèrent que ANN génère la meilleure performance, suivie de SVM et Random Forest, et Naà ¶ ve -Bayes arrivant en dernier.Mots clés : Naive-Bayes, ANN, SVM, Random Forest, Machine Learning, Investment PerformanceClassifications JEL : C11 ; C53 ; C63 ; G11DOI : https://doi.org/10.32479/ijefi.8129

Translated Description (Spanish)

Este estudio tiene como objetivo explorar la predicción del movimiento del precio de las acciones de Taiwán y realizar un análisis de su rendimiento de inversión. Basado en el índice del mercado de valores de Taiwán, el estudio compara cuatro modelos de aprendizaje automático: ANN, SVM, Random Forest y Naöve-Bayes. Con una evaluación del rendimiento de los datos históricos del índice del mercado de valores de Taiwán que abarcan de 2014 a 2018, encontramos: (1) Por medidas de rendimiento general, los modelos de aprendizaje automático superan al índice de mercado de referencia. (2) Por medidas ajustadas al riesgo, los resultados empíricos sugieren que ANN genera el mejor rendimiento, seguido de SVM y Random Forest, y Naöve -Bayes en último lugar. Palabras clave: Naive-Bayes, ANN, SVM, Random Forest, Machine Learning, Investment PerformanceJEL Classifications: C11; C53; C63; G11DOI: https://doi.org/10.32479/ijefi.8129

Files

pdf.pdf

Files (1.1 MB)

⚠️ Please wait a few minutes before your translated files are ready ⚠️ Note: Some files might be protected thus translations might not work.
Name Size Download all
md5:83c8c4f7d9a7dafc20a5aabff5844607
1.1 MB
Preview Download

Additional details

Additional titles

Translated title (Arabic)
تحليل الأداء الاستثماري للتعلم الآلي: فحص تجريبي في سوق الأسهم التايوانية
Translated title (English)
AN ANALYSIS ON INVESTMENT PERFORMANCE OF MACHINE LEARNING: AN EMPIRICAL EXAMINATION ON TAIWAN STOCK MARKET
Translated title (French)
UNE ANALYSE DE LA PERFORMANCE D'INVESTISSEMENT DE L'APPRENTISSAGE AUTOMATIQUE : UN EXAMEN EMPIRIQUE SUR LE MARCHÉ BOUR
Translated title (Spanish)
UN ANÁLISIS SOBRE EL RENDIMIENTO DE LA INVERSIÓN DEL APRENDIZAJE AUTOMÁTICO: UN EXAMEN EMPÍRICO SOBRE EL MERCADO DE VALORES DE TAIWÁN

Identifiers

Other
https://openalex.org/W2953633570
DOI
10.32479/ijefi.8129

Is supplement to
https://openalex.org/W3154045278 (Other)
https://openalex.org/W4367336074 (Other)
https://openalex.org/W4379620016 (Other)
https://openalex.org/W3210764983 (Other)
https://openalex.org/W4367335949 (Other)
https://openalex.org/W3089416646 (Other)
https://openalex.org/W4380048833 (Other)
https://openalex.org/W4285162676 (Other)
https://openalex.org/W3036529732 (Other)
https://openalex.org/W4382052559 (Other)

GreSIS Basics Section

Is Global South Knowledge
Yes
Country
Yemen