Assessing the usefulness of online message board mining in automatic stock prediction systems

We provide evidence of the usefulness of exploiting online text data in stock prediction systems. We do this by mining a popular Argentinian stock message board and empirically answering two questions. First, is there information in the online stock message board useful for predicting stock returns?...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gálvez, R.H., Gravano, A.
Formato: JOUR
Materias:
Latent semantic analysis
Random forest
Ridge regression
Stock market
Text mining
Classification (of information)
Costs
Data mining
Decision trees
Electronic trading
Financial markets
Forecasting
Investments
Learning systems
Regression analysis
Semantics
Classification system
Latent Semantic Analysis
Predictive information
Predictive models
Random forests
Technical indicator
Online systems
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_18777503_v19_n_p43_Galvez
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id todo:paper_18777503_v19_n_p43_Galvez
record_format dspace
spelling todo:paper_18777503_v19_n_p43_Galvez2023-10-03T16:34:18Z Assessing the usefulness of online message board mining in automatic stock prediction systems Gálvez, R.H. Gravano, A. Latent semantic analysis Random forest Ridge regression Stock market Text mining Classification (of information) Costs Data mining Decision trees Electronic trading Financial markets Forecasting Investments Learning systems Regression analysis Semantics Classification system Latent Semantic Analysis Predictive information Predictive models Random forests Ridge regression Technical indicator Text mining Online systems We provide evidence of the usefulness of exploiting online text data in stock prediction systems. We do this by mining a popular Argentinian stock message board and empirically answering two questions. First, is there information in the online stock message board useful for predicting stock returns? Second, if useful information is found, is it novel or it is simply a different way of expressing information already available in the past behavior of stock prices? To address these questions, we build and validate a series of predictive models using state-of-the-art machine learning and topic discovery techniques. Running experiments in which the models are trained with different combinations of features extracted from the past behavior of stock prices, or mined from the online message boards. Evidence suggests that it is possible to extract predictive information from stock message boards. Furthermore, we find that adding this information improves the performance of classification systems trained solely on technical indicators. Our results suggest that information from online text data is complementary to the one available in the past evolution of stock prices. Additionally, we find that highly predictive features derived from the message board data seem to have an important and relevant semantic content. © 2017 Elsevier B.V. Fil:Gravano, A. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_18777503_v19_n_p43_Galvez
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Latent semantic analysis
Random forest
Ridge regression
Stock market
Text mining
Classification (of information)
Costs
Data mining
Decision trees
Electronic trading
Financial markets
Forecasting
Investments
Learning systems
Regression analysis
Semantics
Classification system
Latent Semantic Analysis
Predictive information
Predictive models
Random forests
Ridge regression
Technical indicator
Text mining
Online systems
spellingShingle Latent semantic analysis
Random forest
Ridge regression
Stock market
Text mining
Classification (of information)
Costs
Data mining
Decision trees
Electronic trading
Financial markets
Forecasting
Investments
Learning systems
Regression analysis
Semantics
Classification system
Latent Semantic Analysis
Predictive information
Predictive models
Random forests
Ridge regression
Technical indicator
Text mining
Online systems
Gálvez, R.H.
Gravano, A.
Assessing the usefulness of online message board mining in automatic stock prediction systems
topic_facet Latent semantic analysis
Random forest
Ridge regression
Stock market
Text mining
Classification (of information)
Costs
Data mining
Decision trees
Electronic trading
Financial markets
Forecasting
Investments
Learning systems
Regression analysis
Semantics
Classification system
Latent Semantic Analysis
Predictive information
Predictive models
Random forests
Ridge regression
Technical indicator
Text mining
Online systems
description We provide evidence of the usefulness of exploiting online text data in stock prediction systems. We do this by mining a popular Argentinian stock message board and empirically answering two questions. First, is there information in the online stock message board useful for predicting stock returns? Second, if useful information is found, is it novel or it is simply a different way of expressing information already available in the past behavior of stock prices? To address these questions, we build and validate a series of predictive models using state-of-the-art machine learning and topic discovery techniques. Running experiments in which the models are trained with different combinations of features extracted from the past behavior of stock prices, or mined from the online message boards. Evidence suggests that it is possible to extract predictive information from stock message boards. Furthermore, we find that adding this information improves the performance of classification systems trained solely on technical indicators. Our results suggest that information from online text data is complementary to the one available in the past evolution of stock prices. Additionally, we find that highly predictive features derived from the message board data seem to have an important and relevant semantic content. © 2017 Elsevier B.V.
format JOUR
author Gálvez, R.H.
Gravano, A.
author_facet Gálvez, R.H.
Gravano, A.
author_sort Gálvez, R.H.
title Assessing the usefulness of online message board mining in automatic stock prediction systems
title_short Assessing the usefulness of online message board mining in automatic stock prediction systems
title_full Assessing the usefulness of online message board mining in automatic stock prediction systems
title_fullStr Assessing the usefulness of online message board mining in automatic stock prediction systems
title_full_unstemmed Assessing the usefulness of online message board mining in automatic stock prediction systems
title_sort assessing the usefulness of online message board mining in automatic stock prediction systems
url http://hdl.handle.net/20.500.12110/paper_18777503_v19_n_p43_Galvez
work_keys_str_mv AT galvezrh assessingtheusefulnessofonlinemessageboardmininginautomaticstockpredictionsystems
AT gravanoa assessingtheusefulnessofonlinemessageboardmininginautomaticstockpredictionsystems
_version_ 1782027638080012288

Ejemplares similares