See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/331345883

Stock Market Prediction Using Machine Learning

Conference Paper · December 2018

DOI: 10.1109/ICSCCC.2018.8703332

CITATIONS READS
7 12,531

7 authors, including:

Lokesh Chouhan Navanshu Agarwal

National Institute of Technology, Hamirpur National Institute of Technology, Hamirpur
37 PUBLICATIONS   43 CITATIONS    5 PUBLICATIONS   7 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

A Survey on Applications of Machine Learning in Wireless Sensor Networks View project

SYSTEM AND METHOD FOR FILTERING OF PACKETS BASED ON THE IDENTITY OF THE DEVICE View project

All content following this page was uploaded by Lokesh Chouhan on 15 April 2019.

The user has requested enhancement of the downloaded file.

 Stock Market Prediction Using Machine Learning
Ishita Parmar, Navanshu Agarwal, Sheirsh Saxena, Ridam Arora, Shikhin Gupta, Himanshu Dhiman, Lokesh Chouhan
Department of Computer Science and Engineering
National Institute Of Technology, Hamirpur – 177005, INDIA
cs14mi515, [email protected]
Abstract-In Stock Market Prediction, the aim is to The rest of the paper consists of following: Part 2 puts
predict the future value of the financial stocks of a forward the two models used and the methods used in
company. The recent trend in stock market prediction them in detail. Part 3 discusses the results produced with
technologies is the use of machine learning which different plots for both the models in detail. Part 4
makes predictions based on the values of current stock consists of conclusion and the last section involves the
market indices by training on their previous values. references.
Machine learning itself employs different models to
make prediction easier and authentic. The paper II. METHODOLOGY
focuses on the use of Regression and LSTM based Stock market prediction seems a complex problem
Machine learning to predict stock values. Factors because there are many factors that have yet to be
considered are open, close, low, high and volume. addressed and it doesn’t seem statistical at first. But by
proper use of machine learning techniques, one can
Index Terms- Close, high, low,LSTM model, open, relate previous data to the current data and train the
regression, and volume. machine to learn from it and make appropriate
I. INTRODUCTION assumptions. Machine learning as such has many
models but this paper focuses on two most important of
A correct prediction of stocks can lead to huge them and made the predictions using them.
profits for the seller and the broker. Frequently, it is
brought out that prediction is chaotic rather than 2.1 Regression Based Model
random, which means it can be predicted by carefully
analyzing the history of respective stock market.
Machine learning is an efficient way to represent such
processes. It predicts a market value close to the
tangible value, thereby increasing the accuracy.
Introduction of machine learning to the area of stock
prediction has appealed to many researches because of
its efficient and accurate measurements [1].
The vital part of machine learning is the dataset
used. The dataset should be as concrete as possible
because a little change in the data can perpetuate
massive changes in the outcome [2]. In this project,
supervised machine learning is employed on a dataset
obtained from Yahoo Finance. This dataset comprises of
following five variables: open, close, low, high and
volume. Open, close, low and high are different bid
prices for the stock at separate times with nearly direct
names. The volume is the number of shares that passed
from one owner to another during the time period. The
model is then tested on the test data.
Regression and LSTM models are engaged for this
conjecture separately. Regression involves minimizing
error and LSTM [3][4] contributes to remembering the
data and results for the long run. Finally, the graphs for
the fluctuation of prices with the dates (in case of
Regression based model) and between actual and
Figure 1. Flow Chart for Regression Based Model
predicted price (for the LSTM based model) are plotted.
 Regression is used for predicting continuous values LSTM is the advanced version of Recurrent-Neural-
through some given independent values [5]. The project Networks (RNN) where the information belonging to
is based upon the use of linear regression algorithm for previous state persists. These are different from RNNs
predicting correct values by minimizing the error as they involve long term dependencies and RNNs
function as given in Figure1. This operation is called works on finding the relationship between the recent and
gradient descent. Regression uses a given linear function the current information. This indicates that the interval
for predicting continuous values: of information is relatively smaller than that to LSTM.
The main purpose behind using this model in stock
market prediction is that the predictions depends on
Where, Vis acontinuous value; K represents known large amounts of data and are generally dependent on
independent values; and, a, b are coefficients. the long term history of the market [6]. So LSTM
regulates error by giving an aid to the RNNs through
Work was carried out on csv format of data through retaining information for older stages making the
panda library and calculated the parameter which is to prediction more accurate [7].
be predicted, the price of the stocks with respect to time.
The data is divided into different train sets for cross Since stock market involves processing of huge data,
validation to avoid over fitting. The test set is generally the gradients with respect to the weight matrix may
kept 20% of the whole dataset. Linear regression as become very small and may degrade the learning rate of
given by the above equation is performed on the data the system. This corresponds to the problem of
and then predictions are made, which are plotted to Vanishing Gradient. LSTM prevents this from
show the results of the stock market prices vs time [6]. happening. The LSTM consists of a remembering cell,
input gate, output gate and a forget gate. The cell
2.2 Long Short Term Memory (LSTM) Network Based remembers the value for long term propagation and the
Model gates regulate them [8].
In this paper, a sequential model has been made
which involves stacking two LSTM layers on top of
each other with the output value of 256. The input to the
layer is in the form of two layer [0] and layer[1]. A
dropout value of 0.3 has been fixed which means that
0.3 out of total nodes will be frozen during the training
process to avoid over-fitting of data and increase the
speed of the training process. At last, the core dense
layer where each neuron is connected to every other in
the next layer is added providing input of 32 parameters
to the next core layer which gives output as 1. The
model is compiled with a mean square cost function to
maintain the error throughout the process and accuracy
is chosen as a metric for the prediction [9].
III. EXPERIMENTAL RESULTS
The proposed system is trained and tested over the
dataset taken from Yahoo Finance. It is split into
training and testing sets respectively and yields the
following results upon passing through the different
models:
3.1 Regression Based Model Results
The plot in figure3 is the result of application of linear
regression algorithm on the dataset to predict varying
prices with respect to the time.
Figure 2. LSTM Layers
 than the one being utilized currently. This would help to
increase the accuracy of our prediction models.
Furthermore, other models of Machine Learning could
also be studied to check for the accuracy rate resulted by
them.
REFERENCES
[1] M. Usmani, S. H. Adil, K. Raza and S. S. A. Ali, "Stock
market prediction using machine learning
techniques," 2016 3rd International Conference on
Computer and Information Sciences (ICCOINS), Kuala
Lumpur, 2016, pp. 322-327.
[2] K. Raza, "Prediction of Stock Market performance by
using machine learning techniques," 2017 International
Figure 3. Plot between Price and Date Using Regression Conference on Innovations in Electrical Engineering and
Computational Technologies (ICIEECT), Karachi, 2017,
3.2 LSTM Based Model Results pp. 1-1.
[3] H. Gunduz, Z. Cataltepe and Y. Yaslan, "Stock market
direction prediction using deep neural networks," 2017
25th Signal Processing and Communications
Applications Conference (SIU), Antalya, 2017, pp. 1-4.
[4] M. Billah, S. Waheed and A. Hanifa, "Stock market
prediction using an improved training algorithm of
neural network," 2016 2nd International Conference on
Electrical, Computer & Telecommunication Engineering
(ICECTE), Rajshahi, 2016, pp. 1-4.
[5] H. L. Siew and M. J. Nordin, "Regression techniques for
the prediction of stock price trend," 2012 International
Conference on Statistics in Science, Business and
Engineering (ICSSBE), Langkawi, 2012, pp. 1-5.
[6] K. V. Sujatha and S. M. Sundaram, "Stock index
prediction using regression and neural network models
under non normal conditions," INTERACT-2010,
Figure 4. Plot between Actual and Predicted Trend of Chennai, 2010, pp. 59-63.
[7] S. Liu, G. Liao and Y. Ding, "Stock transaction prediction
LSTM
modeling and analysis based on LSTM," 2018 13th IEEE
The above graph figure 3 is plot over the data having Conference on Industrial Electronics and Applications
batch size 512 and 90 epochs. The prediction is shown (ICIEA), Wuhan, 2018, pp. 2787-2790.
[8] T. Gao, Y. Chai and Y. Liu, "Applying long short term
by red line and the actual trend is shown by blue. The
momory neural networks for predicting stock closing
proximity of these two lines tells, how efficient the price," 2017 8th IEEE International Conference on
LSTM based model is. The prediction approximates real Software Engineering and Service Science (ICSESS),
trend when a considerable amount of time has passed. Beijing, 2017, pp. 575-578.
The more thesystem is trained the greater the accuracy [9] K. A. Althelaya, E. M. El-Alfy and S. Mohammed,
which will be attained "Evaluation of bidirectional LSTM for short-and long-
term stock market prediction," 2018 9th International
IV. CONCLUSION Conference on Information and Communication Systems
Two techniques have been utilized in this paper: (ICICS), Irbid, 2018, pp. 151-156
LSTM and Regression, on the Yahoo finance dataset.
Both the techniques have shown an improvement in the
accuracy of predictions, thereby yielding positive
results. Use of recently introduced machine learning
techniques in the prediction of stocks have yielded
promising results and thereby marked the use of them in
profitable exchange schemes. It has led to the
conclusion that it is possible to predict stock market
with more accuracy and efficiency using machine
learning techniques.
In the future, the stock market prediction system can
be further improved by utilizing a much bigger dataset

View publication stats