Predicting researchers, investing communities and enthusiasts as itprovides
Predicting Market Reactions Using Articial IntelligenceRuchira Ray and Prakhar KhandelwalAbstract — The stock market is a crucial component of anyeconomy in the world. It is a way for companies to gain capitalfor its day to day functions. It enables stock brokers to tradesecurities, bonds and equities in a market. Once a share is listedon the stock market, it can be bought and sold by traders,investors or the general public. Recently, a lot of work hasbeen done to predict the movement of the market.
Forecastingthe movement of the stock market is gaining momentum amongvarious researchers, investing communities and enthusiasts as itprovides better guidance with respect to investing. Predictabilityis one of the major factors which, the protability of tradingin stock and investing is dependent on. The prots earned byinvestment and trading in the stock market depend on thepredictability of the stock, to a large extent. If any systemis developed which can consistently predict the trends of thedynamic stock market, would make the owner of the systemwealthy.
Moreover, the predicted trends of the market will helpthe regulators to make corrective measures to stabilize themarket. Many expert practitioners and researchers have putforward several models using various technical, fundamentaland analytical techniques to give a more or less prediction onthe stock market pattern.I. INTRODUCTIONStock market trading is a renowned way of earning moneyin a short span of time. Investors nd it very difcult topredict the market prices. The prices not only depend onnancial events and the companys performance but also onthe psychology of people investing in the market.
In thissurvey paper, we have tried to analyze the work done inpast few years in the eld of stock market prediction. Wehave examined the techniques used and results achievedby the fellow researchers. We have also tried to study theshortcomings of their work in this paper.II. RELATED WORKThe stock market is a very rewarding eld and hasgenerated interest from a lot of researchers. A considerablylarge number of intelligent people have made models topredict the outcome of the market. Machine learning andarticial intelligence enable us to make intelligent models toforecast market movements.
In this survey paper, we havetried to analyze the work done by fellow researchers in theeld of stock market prediction.A. Stock market prediction using machine learning tech-niquesThe paper on Stock market prediction using machinelearning techniques by Mehak Usmani, Syed Hasan Adil,Kamran Raza, and Syed Saad Azhar Ali predicts the per-formance of Karachi Stock Exchange (KSE) on day closing.Their methodology uses single-layer perceptron, multi-layer perceptron, radial basis function and support vector ma-chines. The factors used as input attributes are market history,news, general public mood, commodity price, interest rate,and foreign exchange.
As per their simulation, the multi-layerperceptron achieved an accuracy of 77 percent. Further, itwas realized that petrol price was the most related attribute,whereas foreign exchange had no impact on stock prices.current designationsB. Intelligent Stock Data Prediction using Predictive DataMiningIn the year 2016, the paper on Intelligent Stock Data Pre-diction using Predictive Data Mining Techniques by Dr. AnjuBala and Pankaj Kumar shed light on predictive data miningalgorithm for market prediction.
Their dataset consists of 21features followed by 57772 data entries and target at the 22ndposition. They classied the data based on the decision tree,linear model and random forest. Their analysis shows thatthe accuracy of the random forest is higher than the linearmodel and decision tree. As an extension to their work, wecan merge various models to gain more accuracy.C. Short Term Stock Price Prediction using Deep LearningTechniquesThe use of deep learning techniques to predict short-termstock market prices was shown in the paper presented byKaustubh Khare, Omkar Darekar, Prafull Gupta and Dr.
The paper titled Short Term Stock Price PredictionUsing Deep Learning Techniques attempts to forecast thetransient future prices of the stock under consideration.Their methodology makes use of Feed Forward MultilayerPerceptron and Long Short-Term Memory model to analyzethe market. The dataset consists of a minute to a minutestock price of 10 shares listed on NSE, over the period ofone year. Each stock consists of 85000 to 90000 points. Thestudy shows that MLPs have performed better at predictingshort-term stock market price than LSTM.
To extend further,we can use the Indian Stock Market data and build a platformto conduct trades based on data obtained.D. Predicting Market Prices using Deep Learning Tech-niquesOne more research was conducted on the effect of deeplearning techniques on stock price prediction. The researchconducted by Nishanth C, Dr. V K Gopal, Vinayakumar R,Lakshmi Nambiar, and Dileep G Menon, titled PredictingMarket Prices Using Deep Learning Techniques uses amodel-independent approach. As opposed to previous re-searchers, the authors have used Recurrent Neural Network,Long Short-Term Memory and Gated Recurrent Unit in theirmodel. Tata Motors and Syndicate Bank data was used totrain and predict the data in their respective elds.
Themodel obtained the best result under the LSTM approach.To capture irregular changes in the stock market, we canuse the Convolution Neural Network as an extension to theexisting model.E. Analyzing stock price chnages using event-related TwitterFeedsSatyabrata Aich, Hee-Cheol Kim, Mangal Sain, and BijayBhaskar Deo conducted a research to analyze the sentimentsof people, and its effect on stock market using data fromthe Twitter platform. The paper titled, Analyzing stock pricechanges using event-related Twitter feeds, outlines the stockprices changes based on the event-related day wise tweetsentiment score. They used Tweepy, a python library toaccess the Twitter API. The tweets were ltered based onthe keyword Samsung .
A collection of 200000 tweets weremade on the launch of galaxy note 7. Sentiment analysisand keyword analysis was carried out on the given data. Theywere able to nd some positive correlation between data sets.
In the future, more tweets with different techniques can beanalyzed for a better performance.F. Proposed System for Estimating Intrinsic Value of StockUsing Monte Carlo SimulationSehba Shahabuddin Siddiqui and Vandana A. Patil con-ducted a research to propose a system for estimating intrinsicvalue of stock using Monte Carlo Stimulation. Based onthe drawbacks of the existing system, they tried to ndintrinsic values and displayed the results by visualisation.Their shortcoming was the low delta factor which can befurther improved.
In future, values of past and prospectiveinvestments can be calibrated.G. Survey of Stock Market Prediction using Machine Learn-ing ApproachAshish Sharma, Dinesh Bhuriya and Upendra Singh anal-ysed the stock market values to predict future values usingregression. What they faced as shortcoming was the lackof t in the least squares approach. In future, multipleregression approach can be improved by using more numberof variables.H. A Review of Stock Market Prediction with ArticialNeural Network (ANN)Chang Sim Vui, Gan Kim Soon, Chin Kim On, and RaynerAlfred, Patricia Anthony gave an overview or survey onmarket prediction using articial neural networks where itwas found that the conventional ANN has lower accuracy.
This paper can be referred to as an introductory material.I. Stock Market Prediction Using an Improved TrainingAlgorithm of Neural NetworkMustain Billah, Sajjad Waheed and Abu Hanifa usedAdaptive Neuro Fuzzy Inference Systems(ANFIS) for better results than Neural Networks for stock prediction. In this pa-per, they used Levenberg Marquard(LM) training algorithmof ANN, which can predict the day end closing stock pricewith less memory and time. This technique can predict stockprice with 53 percent less error than Adaptive Neuro FuzzyInference System and Traditional LM algorithm. It requires30 percent less time, 54 percent less memory than traditionalLM and 47 percent less time, 59 percent less memory thanANFIS.
J. Stock Prediction and Analysis Using Intermittent TrainingData With Articial Neural NetworksN. Srinivasan and C.
Lakshmi did a research, where basedon Multiple layer neural networks they have predicted thestock market values. The training vector along with trainingdata had input layers towards the output layers.This tech-nique foretells the prices of stocks and shares of companiesindexed under National Stock Exchange.
ACKNOWLEDGMENTWe would like to express our deep gratitude to Dr.Baranidharan Balakrishnan our project guide, for her patientguidance, enthusiastic encouragement and useful critiqueson this project work. She has helped on every stage of theproject. His willingness to give us so much of his time isvery much appreciated.We would also like to thank Mrs. S.
S.Saranya and Mr.Arul Prakash for her advice and assistance in keeping ourprogress on schedule.
We are really grateful for her helpin nding the papers and also for her valuable suggestionsthroughout the semester. Our grateful thanks are also extended to our HOD Dr. B.Amutha for the encouragement and providing all the facilitiesin the department.RE F E R E N C E S1 Ian Leifer, Lev Leifer, Small Business Valuation with Use of Cash Flow Stochastic Modeling, in Second International Symposium onStochastic Models in Reliability Engineering, Life Science and Oper-ations Management, pp. 511-516,IEEE,2016.
2 Sehba Shahabuddin Siddiqui, Vandana A. Patil, Proposed system for estimating intrinsic value of value of stock using monte carlosimulation, in International Conference on Intelligent Computing andControl Systems, ICICCS 20173 Ashish Sharma, Dinesh Bhuriya, Upendra Singh, Survey of stockmarket prediction using Machine learning approach, International Con-ference on Electronics, Communication and Aerospace Technology,ICECA 20174 M.P.
Naeini, H. Taremian, and H.B. Hashemi, Stock market value pre- diction using neural networks, International Conference on ComputerInformation Systems and Industrial Management Applications (CISIM2010), pp. 132-136, 2010.5 M.
Mehrara, A. Moeini, M. Ahrari, and A.
Ghafari, Using Technical Analysis with Neural Network for Prediction Stock Price Index inTehran Stock Exchange, Middle Eastern Finance and Economics, vol.6(6), pp. 50-61, 2010.6 R. Dase, and D.
Pawar, Application of articial neural network for stock market predictions: a review of literature, International Journalof Machine Intelligence, vol. 2(2), pp. 1417, 2010. InternationalConference on Computer and Network Technology (ICCNT), pp.