Predictive Analysis of Cryptocurrencies for Developing an Interactive Cryptocurrency Chatbot using IBM Watson Assistant
A. Shamila Ebenezer1, S. Jebapriya2, B. Jefferson Raja Bose3

1A. Shamila Ebenezer, Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
2S. Jebapriya, Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India.
3B. Jefferson Raja Bose, Department of Mechanical Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India

Manuscript received on 05 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 436-447 | Volume-8 Issue-10, August 2019 | Retrieval Number: I8485078919/2019©BEIESP | DOI: 10.35940/ijitee.I8485.0881019
Open Access | Ethics and  Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The main objective of this paper is to analyze the characteristics and features that affects the fluctuations of cryptocurrency prices and to develop aninteractive cryptocurrency chat bot for providing the predictive analysis of cryptocurrency prices. The chatbot is developed using IBM Watson assistant service. The predictive analytics is performed by analyzing the datasets of various cryptocurrencies and applying appropriate time series models. Time Series Forecasting is used for predicting the future values of the prices. Predictive models like ARIMA model is used for calculating the mean squared error of the fitted model. Facebook’s package prophet () which implements a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly and weekly seasonality are further used to predict cryptocurrency prices.
Keywords: Time series data analytics, ARIMA, Cryptocurrency, prophet, Watson
Scope of the Article: Predictive Analysis