A Project Based Seminar Report
On
“Prediction On Stock Prices using Machine Learning”
Subbmitted to the
Savitribai Phule Pune University
In partial fulfillment for the award of the Degree of
Bachelor Of Engineering
In
Information Technology
By
Saurabh Gawade
(307019 & TE-01)
Under the guidance of
Prof.Jaybhaye S.M.
Sinhgad Institutes
Department Of Information Technology
STES’s Sinhgad College Of Engineering
Vadgaon(BK),sinhgad road,Pune 411041
Contents Covered
■ Project Group
■ Project Motivation
■ Introduction
■ Literature review
■ What is Machine Language
■ Study model & Procedures
■ Algorithm
■ Conclusion
■ References
Project Details
• :
.
Project Domain: Machine Learning
•
- 307019 Saurabh Gawade
- 307059 Rushikesh Wankede
- 307070 Shital Bhagat
- 307068 Arya Awachare
Motivation:
■ Using a keras long short term memory (Lstm) model to
predict stock prices .Lstm are very powerful in sequence
prediction problems because they are able to store past
information.
■ Need of project: To detect the future stock prices.
Introduction
- Lstm are widely used
sequence prediction
problems and proven
extremely effective.
-lstm is able to store past
information
Objectives
■ The LSTM model is very popular in time
series forecasting .
■ The LSTM model is trained on entire
dataset ,and for testing purpose.
Literature review-
*Stock prices forecasting
Predicting stock prices is very important for
finance practitioners to best allocate their assets
and to academics to build better and more
accurate asset pricing models. Predicting stock
returns gives crucial implications about market
efficiency. Prediction of future movement of stock
prices has always been a challenging task for the
researchers. In fact, investors are highly interested
in the research area of stock price prediction. Time
series forecasting analyzes past data and projects
estimates of future data values. Basically, this
method attempts to model a nonlinear function by
a recurrence relation derived from past values.
What is Machine Learning
- Definition :
- Machine Learning is an Application of Artificial Intelligence (AI) it gives
devices the ability to learn from their experiences and improve their self
without doing any coding. For Example, when you shop from any website
it’s shows related search like:- People who bought also saw this.
-
-
-
- ML Process :
There are five core tasks in the common ML workflow:
• Get Data. The first step in the Machine Learning process is getting data.
...
• Clean, Prepare & Manipulate Data. Real-world data often has
unorganized, missing, or noisy elements. ...
• Train Model. This step is where the magic happens! ...
• Test Model. ...
• Improve.
Study Model
Fig.1 shows the study model of project
What is dropout layer in neural network?
Dropout is a technique used to prevent a model from
overfitting. Dropout works by randomly setting the outgoing edges of hidden
units (neurons that make up hidden layers) to 0 at each update of the
training phase.
What does dropout do in neural network?
Dropout: A Simple Way to Prevent Neural Networks from Overfitting.
Because the outputs of a layer under dropout are randomly subsampled, it
has the effect of reducing the capacity or thinning the network during
training. As such, a wider network, e.g. more nodes, may be required when
using dropout.
Deep recurrent neural network-
A LSTM-based deep recurrent neural network (DRNN) is a
variant of the recurrent neural network. To enhance the
expressive power of the model, the loop body at each
moment can be repeated many times
Deep recurrent neural network is composed of LSTM, so its
operation mechanism is same as LSTM. During the
process of constructing the task model, the dropout
method was used. Dropout refers to the temporary
discarding of the neural network unit from the network
according to a certain probability during the training of the
deep learning network, which is a means to prevent over-
fitting.
Long short-term memory network-
Long short-term memory network (LSTM) is a particular form of
recurrent neural network (RNN), which is the general term of a series of
neural networks capable of processing sequential data.
LSTM is a special network structure with three “gate” structures
(shown in Fig. 1). Three gates are placed in an LSTM unit, called
input gate, forgetting gate and output gate.
While information enters the LSTM’s network, it can be selected by rules.
Only the information conforms to the algorithm will be left, and the
information that does not conform will be forgotten through the forgetting
gate.
The gate allows information to be passed selectively
and Eq. 1 shows the default activation function of the
LSTM network, the sigmoid function. The LSTM can
add and delete information for neurons through the
gating unit. To determine selectively whether
information passes or not, it consists of a Sigmoid
neural network layer and a pair multiplication
operation. Each element output by the Sigmoid layer
is a real number between [0, 1], representing the
weight through which the corresponding information
passes. In the LSTM neural network, there is also a
layer containing tanh activation function which shown
in Eq. 2. It is used for updating the state of neurons
σ(x)=11+e−x
(1)
tanh(x)=ex−e−xex+e−x
(2)
The forgetting gate of the LSTM neural network
determines what information needs to be discarded,
which reads ht−1 and xt, gives the neuron state
Ct−1 a value of 0–1. Equation 3 shows the
calculation method of forgetting probability
ft=σ(Wf⋅[ht−1,xt]+bf)
(3)
where ht−1 represents the output of the previous
neuron and xt is the input of the current neuron. σ is
the sigmoid function
Conclusion
■ In this paper , a multi value associated network model of
lSTM based deep recurreneural network is proposed to
predict multiple prices of stock simultaneously.
■ Average accuracy of each predicted value is over 95%.
■ In finance, time series analysis is used for financial
forecasting such as stock prices, assets, and commodities.
Stock is the most volatile investment with high risk, but with
high return to investors if carefully managed in their portfolio.
References-
[1] Batres-Estrada, B. (2015).
Deep learning for multivariate
financial time series.
[2] Moritz, B., & Zimmermann, T.
(2016). Tree-based conditional
portfolio sorts: The relation
between past and future stock
returns. Available at
SSRN 2740751.
Thank You !!!
