TY - GEN
T1 - Stock prediction based on Bayesian-LSTM
AU - Huang, Biao
AU - Ding, Qiao
AU - Sun, Guozi
AU - Li, Huakang
N1 - Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/2/26
Y1 - 2018/2/26
N2 - Fluctuations in stock market represent the changes in national economic objectively. Some machine learning algorithms, such as linear fitting and sequence mining, are employed to predict the stock market. However, linear fitting faces issue of over-fitting and black relationships with historical data, while sequence mining is short in efficiency and lack dynamic adaptations. This paper builds a modified Bayesian-LSTM (B-LSTM) model for stock prediction. Six indicators of the Chinese stock market in every day are the basic input for LSTM. In order to represent the economic wave, we defined a data set unit by week which means the basic unit in LSTM is data in one week. Furthermore, a Bayesian optimization model is proposed to estimate the unit number dynamically in different economic cycle. The experimental results demonstrated that the B-LSTM increase over 25% prediction than the conventional LSTM.
AB - Fluctuations in stock market represent the changes in national economic objectively. Some machine learning algorithms, such as linear fitting and sequence mining, are employed to predict the stock market. However, linear fitting faces issue of over-fitting and black relationships with historical data, while sequence mining is short in efficiency and lack dynamic adaptations. This paper builds a modified Bayesian-LSTM (B-LSTM) model for stock prediction. Six indicators of the Chinese stock market in every day are the basic input for LSTM. In order to represent the economic wave, we defined a data set unit by week which means the basic unit in LSTM is data in one week. Furthermore, a Bayesian optimization model is proposed to estimate the unit number dynamically in different economic cycle. The experimental results demonstrated that the B-LSTM increase over 25% prediction than the conventional LSTM.
KW - B-LSTM
KW - Bayesian optimization
KW - Data set unit
KW - Stock market
KW - Stock prediction
UR - http://www.scopus.com/inward/record.url?scp=85048333108&partnerID=8YFLogxK
U2 - 10.1145/3195106.3195170
DO - 10.1145/3195106.3195170
M3 - Conference Proceeding
AN - SCOPUS:85048333108
T3 - ACM International Conference Proceeding Series
SP - 128
EP - 133
BT - Proceedingsof 2018 10th International Conference on Machine Learning and Computing, ICMLC 2018
PB - Association for Computing Machinery
T2 - 10th International Conference on Machine Learning and Computing, ICMLC 2018
Y2 - 26 February 2018 through 28 February 2018
ER -