Accurate prediction of stock market prices is a very challenging task due to the volatile and non-linear nature of financial stock markets. A furthermore difficult job is to present these predictions and insights to the users in a human-centric and user-friendly approach. In this paper, a deep learning to predict the closing value of stocks and attempt to respond to the related questions asked by users via chatbot. Long short-term memory (LSTM) model was used in predicting stock market prices based on the data provided by Yahoo Finance, these insights and information is then served to investors through a chatbot. The aim of this paper is to provide full insights in a graphical and an easy to understand manner so that people with no experience in both information technology and financial world can interpret the insights provided by the model. Finally, the results are tested and the chatbot is trained using the wizard of Oz experiment to ensure user satisfaction. The proposed method fetched a MAPE value of 2.38 and the chatbot response was recorded using the aforementioned method.
CITATION STYLE
Halder, A., Saxena, A., & Priya, S. (2022). Stock Market Prediction Through a Chatbot: A Human-Centered AI Approach. In Smart Innovation, Systems and Technologies (Vol. 302, pp. 435–446). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-2541-2_34
Mendeley helps you to discover research relevant for your work.