PREDICTION OF STOCK MARKET PRICES USING MACHINE LEARNING

PROJECT VIVA VOCE ON 04/10/2023

Presented By
GIRI R (202071019)
GIRINATH P (202071021)
BHARATHI RAJA J (202071004)
MAHALINGAM S (202071043)
VII –Sem.B.Tech.(I.T)

DEPARTMENT OF INFORMATION TECHNOLOGY

MAHENDRA ENGINEERING COLLEGE
(AUTONOMOUS)
MAHENDHIRAPURI, NAMAKKAL Dt.-637 503.
 INTRODUCTION

 Stock Market Price Prediction using machine learning is the process of predicting the future value
of a stock traded on a stock exchange for profits.
 A misconception is also associated with people that buying and selling of the stocks /shares in the
market is an act of gambling .This misconception can be changed and bringing awareness among
people for this.
 Over the past few years, 90 percent of the data in the world has been created as a result of the
creation of 2.5 quintillion bytes of data on a daily basis. A very large amount of data is generated
by financial market. It's very difficult for a trader to recognize a pattern and then devise an optimal
strategy for making decisions. Predicting how the stock market will perform is one of the most
difficult things to do.
 ABSTRACT

The prediction of stock prices has always been a challenging task due to the complexity and
volatility of financial markets. In recent years, machine learning algorithms have gained significant
attention for their ability to analyze historical data and make accurate predictions. We utilize
historical stock market data, including historical prices, trading volumes, and relevant financial
indicators, to train and evaluate different machine learning models. Several popular machine learning
algorithms, such as Long Short-Term Memory (LSTM) networks are employed to predict future
stock prices based on past patterns and market trends. We actually have four algorithms , at the end
which algorithm is the best among these which gives the best accuracy for the stock market price
prediction. Finally which one provides the highest accuracy for generating the output.
 LITERATURE REVIEW

A systematic review of fundamental and technical analysis of stock market predictions

The stock market is a key pivot in every growing and thriving economy, and every investment in the market is
aimed at maximizingprofits and minimizing associated risk. As a result, numerous studies have been conducted
on the stock-market prediction using technical or fundamental analysis through various soft-computing
techniques and algorithms. This study attempted to undertake a systematic and critical review of about one
hundred and twenty-two (122) pertinent research works reported in academic journals over 11 years (2007–
2018) in the area of stock market prediction using machine learning. The various techniques identified from
these reports were clustered into three categories, namely technical, fundamental, and combined analyses.
 LITERATURE REVIEW

New efficient hybrid candlestick technical analysis model for stock market timing on the basis of the
support vector machine and heuristic algorithms of imperialist competition and genetic

In this paper, two hybrid models are used for timing of the stock markets on the basis of the technical analysis
of Japanese Candlestick by Support Vector Machine (SVM) and Heuristic Algorithms of Imperialist
Competition and Genetic. In the first model, SVM and Imperialist Competition Algorithm (ICA) are developed
for stock market timing in which ICA is used to optimize the SVM parameters. In the second model, SVM is
used with Genetic Algorithm (GA) where GA is used for feature selection in addition to SVM parameters
optimization. Here the two approaches, Raw-based and Signal-based are devised on the basis of the literature to
generate the input data of the model.
 LITERATURE REVIEW

An explanation for the predictive success of technical analysis

This paper documents clustering in currency stop-loss and take-pro¢t orders, and uses that clustering to provide
an explanation for two familiar predictions from technical analysis: trends tend to reverse course at predictable
support and resistance levels, and trends tend to be unusually rapid after rates cross such levels.The data are the
¢rst available on individual currency stop-loss and take-pro¢t orders. Take-pro¢t orders cluster particularly
strongly at round numbers, which could explain the ¢rst prediction. Stop-loss orders cluster strongly just beyond
round numbers, which could explain the second prediction.
 LITERATURE REVIEW

Predicting recessions with boosted regression trees

We use a machine-learning approach known as boosted regression trees (BRT) to reexamine the usefulness of
selected leading indicators for predicting recessions. We estimate the BRT approach on German data and study
the relative importance of the indicators and their marginal effects on the probability of a recession. Our results
show that measures of the short-term interest rate and the term spread are important leading indicators. The
recession probability is a nonlinear function of these leading indicators. The BRT approach also helps to
uncover the way in which the recession probability depends on the interactions between the leading indicators.
While the predictive power of the shortterm interest rates has declined over time, the term spread and the stock
market have gained in importance. The BRT approach shows a better out-of-sample performance than popular
profit approaches.
 LITERATURE REVIEW

Fusion of multiple diverse predictors in stock market

Forecasting stock returns and their risk represents one of the most important concerns of market decision
makers. Although many studies have examined single classifiers of stock returns and risk methods, fusion
methods, which have only recently emerged, require further study in this area. The main aim of this paper is to
propose a fusion model based on the use of multiple diverse base classifiers that operate on a common input and
a Meta classifier that learns from base classifiers’ outputs to obtain more precise stock return and risk
predictions. A set of diversity methods, including Bagging,
 EXISTING SYSTEM


The stock market is an interesting industry to study. There are various variations present in it.
Many experts have been studying and researching on the various trends that the stock market goes
through. One of the major studies has been the attempt to predict the stock prices of various
companies based on historical data. Prediction of stock prices will greatly help people to
understand where and how to invest so that the risk of losing money is minimized.
Many researchers are looking at machine learning and deep learning as possible ways to predict
stock prices. The existing system works in two methods Regression and Classification.
In regression, the system predicts the closing price of stock of a company, and in classification,
the system predicts whether the closing price of stock will increase or decrease the next day.
 DRAWBACK OF EXISITING SYSTEM

The stock market is a complex system, and there is a lot of data that needs to be collected and
analyzed in order to make accurate predictions.

 Noise can be caused by a variety of factors, such as typos, errors in data entry, or missing values. This
can make it difficult to train a machine learning model that can accurately predict stock prices.

This can lead to inaccurate predictions, especially if the training data is not representative of the real
world.

The stock market is a volatile market, which means that prices can change rapidly and unpredictably.
This can make it difficult for machine learning models to accurately predict stock prices, especially in
the short term.
 PROPOSED SYSTEM

The proposed system aims to leverage the power of machine learning algorithms for accurate stock
price prediction in the dynamic and volatile landscape of financial markets.

Through a comprehensive approach, historical stock market data encompassing price trends,
trading volumes, and pertinent financial indicators will be meticulously preprocessed and
engineered.

This enriched dataset will serve as the foundation for training and evaluating a diverse range of
machine learning models.

 These models, including Long Short-Term Memory (LSTM) networks, will be meticulously tuned
and validated using appropriate cross-validation or time series techniques.
 SYSTEM REQUIREMENTS SPECIFICATION

 Hardware Requirements:
Processor :Intel Core i5
RAM :8 GB
Hard disk :512 GB

 Software Requirements:
Operating System :Windows 11
Software tool :Eclipse IDE(V10)
Language :Java(JDK 1.8)
 FLOW DIAGRAM

LOAD DATASET

PRE-PROCESSING TRAINING

CLASSIFICATION USING LSTM,

TESTING
SVM , RF AND GRADIENT
BOOSTING

RESULT ANALYSIS
 MODULES

• INPUT DATASET

• LSTM implementation

• Performance analysis
 INPUT AND OUTPUT DESIGN

• The input design for a stock market price prediction model should include all of the relevant features that can
affect stock prices. This may include historical prices, trading volumes, financial indicators, and news events.
The data should be cleaned and preprocessed before it is used to train the model.

• The output design for a stock market price prediction model should be tailored to the specific prediction task
that you are trying to solve. For example, if you are trying to predict the closing price of a stock for the next
day, then the output should be a single number representing the predicted closing price. If you are trying to
predict the direction of the stock market (up or down), then the output should be a binary classification label.
 REFERENCES

• I. K. Nti, A. F. Adekoya, and B. A. Weyori, ‘‘A systematic review offundamental and technical analysis of stock market
predictions,’’ Artif.Intell. Rev., vol. 53, pp. 1–51, Aug. 2020.

• E. Ahmadi, M. Jasemi, L. Monplaisir, M. A. Nabavi, A. Mahmoodi, andP. A. Jam, ‘‘New efficient hybrid candlestick technical
analysis modelfor stock market timing on the basis of the support vector machine andheuristic algorithms of imperialist
competition and genetic,’’ Expert Syst.Appl., vol. 94, pp. 21–31, Mar. 2022

• C. L. Osler, ‘‘Currency orders and exchange rate dynamics: An explanationfor the predictive success of technical analysis,’’ J.
Finance, vol. 58, no. 5,pp. 1791–1819, Oct. 2021 doi: 10.1111/1540-6261.00588.

• J. Dopke, U. Fritsche, and C. Pierdzioch, ‘‘Predicting recessions withboosted regression trees,’’ Int. J. Forecasting, vol. 33, no.
4, pp. 745–759, 2021

• S. Barak, A. Arjmand, and S. Ortobelli, ‘‘Fusion of multiple diversepredictors in stock market,’’ Inf. Fusion, vol. 36, pp. 90–
102, Jul. 2020
THANK YOU!