ACCENT JOURNAL OF ECONOMICS ECOLOGY & ENGINEERING Peer Reviewed and Refereed Journal (International Journal) ISSN-2456-1037
Vol. 05,Special Issue 01, (ICOSD-2020) January 2020, Available Online: www.ajeee.co.in/index.php/AJEEE
1
STOCK MARKET PREDICTION USING SUPPORT VECTOR MACHINE Richa Jha1, Prachi Kewaliya2 and Harish Patidar3
Student at Department of Computer Science Engineering, RGPV Bhopal, (M.P)1 Student at Department of Computer Science Engineering, RGPV Bhopal, (M.P)2 Professor at Department of Computer Science Engineering, RGPV Bhopal, (M.P)3 Abstract- The “Implementation of Machine Learning for Stock Market Prediction System” is an act of determining the future value of a company or stock traded on a financial exchange.
Support Vector Machine (SVM) is a very specific type of machine learning algorithm characterized by the capacity control of the decision function, the use of the kernel functions and the sparsity of the solution. In this paper, we investigate the predictability of financial movement direction with Support Vector Machine by predicting the weekly movement direction. To evaluate the forecasting ability of SVM, we compare its performance with those of other machine learning algorithms such as linear regression. The experiment results show that Support Vector Machine outperforms other Machine Learning Algorithm like Decision Trees. Further, we propose a combining model by integrating SVM with other classification methods. The combining model performs best among both the forecasting methods. The successful prediction of a stock’s future price will yield a maximum profit to the investor.
Keywords: Author Guide, Article, Camera-Ready Format, Paper Specifications, Paper Submission.
1. INTRODUCTION
Stock price prediction is one of the most widely studied and challenging problems, attracting researchers from many fields including economics, history, finance, mathematics, and computer science. Nevertheless, the challenge of stock forecasting is so appealing because an improvement of just a few percentage points can increase profit by millions of dollars for these institutions [1]. The trend in a stock market prediction is not a new thing and yet this issue is kept being discussed by various organizations. There are two types to analyze stocks which investors perform before investing in a stock, first is the fundamental analysis, in this analysis investors look at the intrinsic value of stocks, and performance of the industry, economy, political climate etc. to decide that whether to invest or not.
On the other hand, the technical analysis, it is an evolution of stocks by the means of studying the statistics generated by market activity, such as past prices and volumes.
Stock Market follows the random walk, which implies that the best prediction you can have about tomorrow’s value is today’s value. This paper will develop a financial data predictor program in which there will be a dataset storing all historical stock prices. The main purpose of the prediction is to reduce uncertainty associated to investment decision making. Stock prices are considered to have quick changes because of underlying nature of the financial domain and because of the mix of a known parameters i.e., previous day’s closing price, and the unknown factor like Rumor.
In the prediction there are two types like: dummy and a real time prediction which is used in stock market prediction system. In Dummy prediction they have define some set of rules and predict the future price of shares by calculating the average price. In the real time prediction compulsory used internet and saw current price of shares of the company.
Computational advances have led to introduction of machine learning techniques for the predictive systems in financial markets. In this paper we focus on a specific machine learning technique known as Support Vector Machines (SVM). Our goal is to use SVM at time t to predict whether a given stock’s price is higher or lower on day t + m.
2. EXISTING METHODS
Time series forecasting consists of a research area designed to solve various problems, mainly in the financial area. Support Vector Regression (SVR), a variant of the SVM is typically used to solve nonlinear regression problems by constructing the input-output mapping function. The least squares support vector regression (LSSVR) algorithm is a further development of SVR and its use considerably reduces computational complexity and increases efficiency compared to standard SVR. The Firefly Algorithm (FA), which is a
nature inspired metaheuristic method, has recently performed extremely well in solving various optimization problems.
2.1 Disadvantages
1. The existing system focuses on the stock price market in Taiwan, but does not generalize for other markets worldwide.
2. The system does not allow the import of raw data directly.
3. The existing system cannot be used to analyse multi-variate time series.
4. Lastly, the system does not have a user-interface which can be distributed as a web app to users for personal use.
3. LITERATURE SURVEY
Pawan Kumbhare, Rohit Makhija and Hitesh Raichandani from SANTACLARA UNIVERSITY [2] studied Stock Market Prediction using Support Vector Machine (SVM) and Decision Trees because it is easy to program in this compared to Artificial Neural Networks. They took input from historical data from Yahoo Finance. Appropriate data would be applied tofind the stock price trends. Hence the prediction model will notify the up or down of the stock price movement for the next trading day and investors can act upon it so as to maximize their chances of gaining a profit. The entire system would be implemented in Python/Java and R language using open source libraries. Hence it will effectively be a zero cost system.
Apar Adhikari, Bibek Subedi, Bikash Ghimirey, Mahesh Karki from Himalaya College of Engineering [3] studied Stock Market Prediction using Artificial Neural Networks.
The system currently computes 63 separate input variables at the close of each trading day.
The 63 inputs are applied to neural networks and after some numbers crunching the network outputs a value between -1.0 and +1.0 with -1.0 being a very strong down market signal and +1.0 being a very strong up market signal. A value near 0 indicates neutral market signal. Sachin Sampat Patil from SSSSIST [4], Sehore studied the Stock Market Trend using Support Vector Machine. Support Vector Machine (SVM) is a relatively new learning algorithm that has the desirable characteristics of the control of the decision function, the use of the kernel method, and the sparsely of the solution.
4. PROBLEM DEFINITION
Investors are familiar with the saying, “buy low, sell high” but this does not provide enough context to make proper investment decisions. Before an investor invests in any stock, he needs to be aware how the stock market behaves. Investing in a good stock but at a bad time can have disastrous results, while investment in a mediocre stock at the right time can bear profits. Financial investors of today are facing this problem of trading as they do not properly understand as to which stocks to buy or which stocks to sell in order to get optimum profits.
Predicting long term value of the stock is relatively easy than predicting on day-to- day basis as the stocks fluctuate rapidly every hour based on world events. Stock exchanges are financial institutions which allow transfer ability of different goods between stock broker components. This anticipation of market can generate profits or losses, depending on the power to predict future values. The best algorithm and system is the one which gives maximum accuracy which can be predicted.
To summarize, following points can define problem statements:-
1. Accuracy: Problem with most of the systems is mainly accuracy. The system which has high degree of accuracy is simply considered best.
2. Yield significant profit: In stock market system, the one that gives maximum accuracy automatically yields maximum profit.
There are so many factors involved in the prediction e.g. Physical factors vs psychological factors, rational and irrational behaviour etc. All these aspects combine to make share prices volatile and very difficult to predict with high level of accuracy.
5. NEED OF PROJECT
Stock market prediction is the act of trying to determine the future value of a company stock or other financial instrument traded on an exchange. The successful prediction of a
stock’s future price could yield significant profit. The efficient-market hypothesis suggests that stock prices reflect all currently available information and any price changes that are not based on newly revealed information thus are inherently unpredictable. Others disagree and those with this viewpoint possess myriad methods and technologies which purportedly allow them to gain future price information.
6. PROPOSED SYSTEM
We will implement the system using different machine learning techniques. We are using Support Vector Machines for the Stock market prediction. The solution to this problem demands the use of tools and technologies related to the field of data mining, pattern recognition, machine learning and data prediction. The application will predict the stock prices for the next trading day. It uses SVM which have better performance than Neural Network. Moreover, using SVM will takes away the burden of matching the present price pattern with historic patterns and also SVM trains faster than a NN and has a lower computational cost.
7. KEY FEATURES
The benefits of stock market could include:-
1. Making it easier for you and other investors - including venture capitalists - to realize their investment.
2. Increasing your public profile, and providing reassurance to your customers and suppliers
3. Creating a market for the company's shares
4. Automatically sale or purchase shares using automation concept.
5. Predict future price of share by using Dummy prediction concept.
6. Predict current shares price by using Real-time prediction concept.
7. Reduce stakeholder’s time.
8. The system to be developed will help to find share market value as per stakeholders need.
9. System maintains the details about the stakeholder and companies and also easily views all details of company and stakeholder.
8. WORKING
In stock market system there are admin do the registration of companies. User do the registration and then login to the system. And see the profile and company details. And perform some operations likes sales and purchase the shares. in this system also perform automation and prediction to predict the shares future price and automatically perform the operations like sale and purchase the shares. Following are the explanation of modules for stock market system.
1. Admin: Admin do the registration of company and users. Admin update the information about the company whenever required. Admin see the list of company and users. Also admin send the message to all users.
2. Company Registration: In Company registration form contain registration phase for new Company. Admin fill all the information about company like company name, shares, price etc. for sale and purchase share.
3. User Registration: In user registration form contain registration phase for new User. Admin fill all the information about user like user name, address, DOB etc. in that admin provide username and password to user.
4. Prediction: The possible market prediction goal can be the future stock price or the volatility of the prices or market trend. In the prediction there are two types like Dummy and Real time prediction. In dummy prediction we define some rules and predict the future price of shares. In the real time prediction use internet and see current price of shares.
5. Automation: In automation user perform two operations like purchase and sale the shares. In that perform operations automatically. Set one price to system after match it automatically purchase or sale.
9. RESULT ANALYSIS
It uses SVM which have better performance than Neural Network. Moreover, using SVM will takes away the burden of matching the present price pattern with historic patterns and also SVM trains faster than a NN and has a lower computational cost.
Fig. 1 Proposed beam former.
10. CONCLUSION
So to summarize, we can say that a Stock Market Prediction System is very useful with the emergence of new technologies and algorithms. In this project, we use of data collected from different global financial markets with machine learning algorithms to predict the stock- market trends. Our conclusion can be summarized into following points: SVM algorithm work on the large dataset value which are collected from different global financial markets.
SVM also does not give a problem of over fitting. Correlation analysis indicates strong interconnection between the Market stock index and global markets that close right before or at the very beginning of trading time. Various machine learning based models are proposed for predicting daily trend of Market stocks. Numerical results suggest high efficiency. The model generates higher profit comparatively.
REFERENCES
1. Sahil Magde, Advisor: Professor Swati Bhatt, “Predicting Stock Price Direction using Support Vector Machine”, Independent Work Report Spring 2015.
2. Pawan Kumbhare, Rohit Makhija and Hitesh Raichandani from SANTA CLARA UNIVERSITY, “Stock Market Prediction”, March 2016 under the supervision of Dr. Ming-Hwa Wang.
3. Apar Adhikari, Bibek Subedi, Bikash Ghimirey, Mahesh Karki from Himalaya College of Engineering,
“Stock Market Analysis and Prediction using Artificial Neural Network”, August 2017.
4. Sachin Sampat Patil from SSSSIST, Sehore, “Stock Market Prediction Using Support Vector Machine”
International Journal of Current Trends in Engineering & Technology Volume: 02, Issue: 01 (JAN-FAB, 2016).
5. “Stock Market Prediction” by Mark Dune, Supervisor: Derek Bridge.
