Stock Market Prediction Using Machine

Learning

Name- Guided by .
Reg no-
RAHUL ANIKTA
2214501118
KUMAR KASHYAP
 GUIDE'S APPROVAL

I have a post graduate master’s degree in Information Technology with

specialization in Data Analytics. I have academic experience in Python,
Machine Learning and R language. Excellent Work Ethics, always well-
dressed, expressive, and soft spoken. I am very flexible and adaptive to
changes.
As a Data Specialist I know how to thrive on finding patterns in large
datasets and translating business requirements into structured datasets.
I have an experience of collaborate with my colleagues to drive data led
decision making across Organisation. By providing the right insights, in
the right way at the right time.
 ABSTRACT

The Stock Market is one of the most active research areas, Stock market is non linear and
volatile . Predicting the Stock Market is quite challenging, and it requires intensive study of
the pattern of data. The stock market has always been a focal point for investors .Stock
market is the one place of investment but the degree of risk is high because of the
change in stock prices happens at every milli-second. In the past ,several researchers
provided several approaches to predict stock prices .The change of price of each stock
depends on the demand for that stock. So it is very difficult to guess the stock prices .
Stock trend forecasting tools are in high demand since they aid in the direct prediction of
stock prices. Various machine learning and deep learning algorithms are used to make
prediction with least inaccuracy.

Keywords: stock prediction , machine learning ,Deep Learning ,LSTM ,BILSTM and GRU.
 Introduction

Stock market allows us to buy

A stock market is a public
and sell units of stocks
market for the trading of
(ownership) of a
company stock.
company.

If more sellers than buyers,

If the company’s profits go up,
stock prices tend to fall.
then we own some of the profits
Conversely, when more buyers
and if they go down, then we
than sellers, stock prices tend
lose profits with them.
to rise
 Problem Statement

To accurately predict Use BILSTM for

the future closing prediction and
value of a given stock compare it against
across a given period LSTM and GRU, a
of time in the future. variant of RNN.
Table 1: Literature review
OUTLINE OF THE PROPOSED MODEL
 Dataset
• Downloaded the dataset from Kaggle.com.
• The Dataset contains data for 5 years ie. from 5th Feb 2018 to 4th Feb 2022
• This is a series of data points indexed in time order or a time series. Our goals is to
predict the closing price for any given date after training
 LSTM

▪ LSTM(Long Short Term Memory)

▪ LSTM are explicitly designed to avoid
the long-term dependency problem.
Remembering information for long
periods of time is practicaly their default
behavior, not something they struggle to
learn!
▪ There are three gates to protect and
control the cell states
▪ 1.Forget gate 2.Input gate 3.Output gate
 LSTM(How it works?)

▪ The key to LSTM is the Memory cell

state which stores the information. It
runs straight down the entire chain.
▪ LSTM has the ability to remove or add
information to these cell state,
regulated by structures called gates
▪ Gates are composed of sigmod neural
net layer and a multiplication
operation.
▪ Sigmoid layer outputs zero or one
 LSTM(How it works?)

Second, input gate

represents “keep the decides which values
First forget gate looks at 1 Combining these two,
information ” and 0 will be updated , in order
h t-1 and xt and outputs a creates an update to the
represent “remove the to do that a tanh layer
number between 0 and 1 state.
information”. creates a vector of ct
(bar).

A sigmoid layer will

Third, it’s time to update Fourth, output will based decides what parts of the
the old cell ct-1 to ct on our cell state cell state we are going to
output.
Bi-LSTM
▪ A Bidirectional LSTM, or biLSTM, is a sequence
processing model that consists of two LSTMs: one
taking the input in a forward direction, and the other
in a backwards direction. BiLSTMs effectively
increase the amount of information available to the
network, improving the context available to the
algorithm (e.g. knowing what words immediately
follow and precede a word in a sentence).
Architecture of Bi-LSTM
 ▪ The basic idea behind GRU is to use
gating mechanisms to selectively
update the hidden state of the
network at each time step. The gating
GRU mechanisms are used to control the
flow of information in and out of the
network. The GRU has two gating
mechanisms, called the reset gate and
the update gate.
 Implementation details

Platform used: Programming Algorithm: Dataset:Netflix Stocks Libraries: Numpy, Data visualization:
Jupyter Notebook Language: Python LSTM/BLSTM historical Time- Panda, Matplotlib, Line graph
series data Tensorflow, Sklearn
True future vs prediction for BiLSTM :
True future vs prediction for LSTM:
True future vs prediction for GRU:
True future vs prediction for CNN-GRU:
CALCULATING 'MAE' AND 'RMSE'
Error(Output):
CALCULATING ACCURACY
ACCURACY (Output):
 Conclusion

▪ In this study, we evaluated the performance of BILSTM ,LSTM , GRU

and hybrid approach (CNN-GRU) deep learning methodology for
stock market prediction. The performance is evaluated on a
benchmark dataset for short- and long-term prediction using two
performance measures. The performances of the tuned
BILSTM compared with unidirectional LSTM and GRU. The results
showed that GRU networks produced better performance for
predicting short-term prices as opposed to the long-term prediction
results. Overall, GRU networks demonstrated better performance
and convergence for both short- and long-term predictions
 References
• Mahadik, Apoorva, Devyani Vaghela, and Amrapali Mhaisgawali. "Stock Price Prediction using LSTM
and ARIMA." In 2021 Second International Conference on Electronics and Sustainable
Communication Systems (ICESC), pp. 1594-1601. IEEE, 2021.
• Bathla, Gourav. "Stock Price prediction using LSTM and SVR." In 2020 Sixth
International Conference on Parallel, Distributed and Grid Computing (PDGC), pp. 211-
214. IEEE, 2020.
• Chen, Shile, and Changjun Zhou. "Stock prediction based on genetic algorithm feature
selection and long short-term memory neural network." IEEE Access 9 (2020): 9066-
9072.
• Kavinnilaa, J., E. Hemalatha, Minu Susan Jacob, and R. Dhanalakshmi. "Stock Price
Prediction Based on LSTM Deep Learning Model." In 2021 International Conference on
System, Computation, Automation and Networking (ICSCAN), pp. 1-4. IEEE, 2021
• Moghar, Adil, and Mhamed Hamiche. "Stock market prediction using LSTM recurrent neural
network." Procedia Computer Science 170 (2020): 1168-1173.
• Ariyo, Adebiyi A., Adewumi O. Adewumi, and Charles K. Ayo. "Stock price prediction using the
ARIMA model." In 2014 UKSim-AMSS 16th international conference on computer modelling and
simulation, pp. 106-112. IEEE, 2014.
• Damrongsakmethee, Thitimanan, and Victor-Emil Neagoe. "Stock market prediction using a
deep learning approach." In 2020 12th International Conference on Electronics, Computers and Artificial
Intelligence (ECAI), pp. 1-6. IEEE, 2020.
• Goswami, Shruti, and Sonal Yadav. "Stock Market Prediction Using Deep Learning
LSTM Model." In 2021 International Conference on Smart Generation Computing, Communication
and Networking (SMART GENCON), pp. 1-5. IEEE, 2021.
• Althelaya, Khaled A., El-Sayed M. El-Alfy, and Salahadin Mohammed. "Evaluation
of bidirectional LSTM for short-and long-term stock market prediction." In 2018
9th international conference on information and communication systems (ICICS), pp. 151-156.
IEEE, 2018.
• Usmani, Mehak, Syed Hasan Adil, Kamran Raza, and Syed Saad Azhar Ali. "Stock market
prediction using machine learning techniques." In 2016 3rd international conference on computer
and information sciences (ICCOINS), pp. 322-327. IEEE, 2016.
• Chong, Lu Sin, Kian Ming Lim, and Chin Poo Lee. "Stock market prediction using ensemble
of deep neural networks." In 2020 IEEE 2nd International Conference on Artificial Intelligence in
Engineering and Technology (IICAIET), pp. 1-5. IEEE, 2020.
• Ojo, Samuel Olusegun, Pius Adewale Owolawi, Maredi Mphahlele, and Juliana Adeola Adisa.
"Stock market behaviour prediction using stacked LSTM networks." In 2019 International
multidisciplinary information technology and engineering conference (IMITEC), pp. 1-5. IEEE, 2019.
• Sawale, Gaurav J., and Manoj K. Rawat. "Stock Market Prediction using Sentiment
Analysis and Machine Learning Approach." In 2022 4th International Conference on Smart
Systems and Inventive Technology (ICSSIT), pp. 1-6. IEEE, 2022.
Thank You