TY - GEN
T1 - Stock Price Movement Prediction Using Technical Analysis and Sentiment Analysis
AU - Sagala, Tommy Wijaya
AU - Saputri, Mei Silviana
AU - Mahendra, Rahmad
AU - Budi, Indra
N1 - Funding Information:
From these facts indicate that the prediction accuracy of stock price movements is low. This is supported by previous studies in predicting stock price movements in the Indonesian stock market which resulted in low accuracy. Research conducted by Setiawan et al. [2] utilizes technical analysis or stock price movements. The performance of the study resulted in an average accuracy of under 60%. In addition, research conducted by Rahmawati [3] who classified the stock price movements in Indonesia using online media sentiment analysis resulted in an average accuracy of 56.53%. Therefore, this study aims to calculate how much the accuracy of the stock price movement classification results using a combination of technical analysis and online media sentiment analysis.
Publisher Copyright:
© 2020 ACM.
PY - 2020/1/17
Y1 - 2020/1/17
N2 - This study aims to predict stock price movement using combination of technical analysis and sentiment analysis. When conducting stock transactions, the traders consider not only market activities but also the sentiments expressed within information reported in media. We build the classifier to categorize the price quotes into one of three classes: "up", "down", and "constant". We conduct the experiment with several algorithms, i.e. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Naïve Bayes. The results of our empirical study is that the highest accuracy achieved from the method combining features from historical data and online media sentiment, on 5 days trading window using the SVM algorithm.
AB - This study aims to predict stock price movement using combination of technical analysis and sentiment analysis. When conducting stock transactions, the traders consider not only market activities but also the sentiments expressed within information reported in media. We build the classifier to categorize the price quotes into one of three classes: "up", "down", and "constant". We conduct the experiment with several algorithms, i.e. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Naïve Bayes. The results of our empirical study is that the highest accuracy achieved from the method combining features from historical data and online media sentiment, on 5 days trading window using the SVM algorithm.
KW - Classification
KW - Price
KW - Sentiment Analysis
KW - Stocks
KW - Technical Analysis
KW - Trader
UR - http://www.scopus.com/inward/record.url?scp=85083038707&partnerID=8YFLogxK
U2 - 10.1145/3379310.3381045
DO - 10.1145/3379310.3381045
M3 - Conference contribution
AN - SCOPUS:85083038707
T3 - ACM International Conference Proceeding Series
SP - 123
EP - 127
BT - APIT 2020 - 2020 2nd Asia Pacific Information Technology Conference
PB - Association for Computing Machinery
T2 - 2nd Asia Pacific Information Technology Conference, APIT 2020
Y2 - 17 January 2020 through 19 January 2020
ER -