Unsupervised Learning Based Stock Price Recommendation using Collaborative Filtering
Pratyush Ranjan Mohapatra1, Santosh Kumar Swain2, Santi Swarup Basa3

1Pratyush Ranjan Mohapatra*, Department of CSE, KIIT Deemed to be University, Bhubaneswar, India.
2Santosh Kumar Swain, Department of CSE, KIIT Deemed to be University, Bhubaneswar, India.
3Santi Swarup Basa, Department of CS, North Orissa University, Baripada, Odisha, India.

Manuscript received on 28 August 2019. | Revised Manuscript received on 09 September 2019. | Manuscript published on 30 September 2019. | PP: 2051-2055 | Volume-8 Issue-11, September 2019. | Retrieval Number: K19320981119/2019©BEIESP | DOI: 10.35940/ijitee.K1932.0981119
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: In this study, 17 stock market data were adopted for long term Prediction of stock price. Now days, Stock market data have got a significant role for invest finance in portfolio management. The various non-linear algorithms and statistical models are used for forecasting of financial data. In this article, we have used application of recommender system for this purpose. We primarily focused on use of machine learning algorithms for developing a stock market data recommender system. Machine learning has become a widely operational tool in financial recommendation systems. Here we considered the daily wise equity trading of Nifty 50 from National Stock Exchange (NSE) of 50 companies in 10 different sectors around 5986 days’ transactions as data. We adopted k-Nearest Neighbors classification algorithm to classify users based recommender system. Collaborative filtering method uses for recommend the stock, the performance measure through RMSE, and R2. The result also reveals that k-NN algorithm shown more accuracy as compare to other existing methods.
Keywords: Classification, Collaborative based filtering, k-Nearest Neighbors, Machine learning
Scope of the Article: