Scribd
Upload
380 views3 pages

Stock Prediction Synopsis

This document outlines a proposed project to predict stock prices of companies on the National Stock Exchange of India using sentiment analysis and artificial neural networks. The project will analyze stock price data and news sentiments to train neural networks to forecast stock movement. Specifically, it will extract stock and sentiment data, preprocess it, use encoders to extract features, train various neural network models, and test the models' predictive accuracy on real stock price data. If successful, the project could be used to guide investment decisions or for algorithmic trading strategies. The proposal draws upon related work applying machine learning to stock prediction but aims to develop the project independently without external collaboration.

Uploaded by

PiyushPurohit
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
380 views3 pages

Stock Prediction Synopsis

This document outlines a proposed project to predict stock prices of companies on the National Stock Exchange of India using sentiment analysis and artificial neural networks. The project will analyze stock price data and news sentiments to train neural networks to forecast stock movement. Specifically, it will extract stock and sentiment data, preprocess it, use encoders to extract features, train various neural network models, and test the models' predictive accuracy on real stock price data. If successful, the project could be used to guide investment decisions or for algorithmic trading strategies. The proposal draws upon related work applying machine learning to stock prediction but aims to develop the project independently without external collaboration.

Uploaded by

PiyushPurohit
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Project Ideas - 2019-20

Name of guide Prof. Kavita Shirsat

Department TE CMPN – A

Technical area/domain of interest/expertise Artificial Intelligence, Machine learning

Brief on recent work

Details about the project

1 Project Title Predicting Stock prices of NSE using Sentiment


Analysis and Artificial Neural Network

2 Domain of the project Artificial Intelligence

3 Pre-requisite for the project 1. Python (Pandas & Keras)


2. Knowledge of financial Markets
 Company and its stock price
 Use of various Indicators
 Financial Ratios
3. Different Neural network architecture like
 deep neural network
 convolution neural network
 deep reinforcement learning
4. Data Mining techniques
5. Quantitative skills to handle large amount of data

4 Project Abstract In this report we analyse existing and new methods


of stock market prediction. We take three different
approaches at the problem: Fundamental analysis,
Technical Analysis, and the application of Machine
Learning. We find evidence in support of the weak
form of the Efficient Market Hypothesis, that the
historic price does not contain useful information
but out of sample data may be predictive. We show
that Fundamental Analysis and Machine Learning
could be used to guide an investor’s decisions. We
demonstrate a common flaw in Technical Analysis
methodology and show that it produces limited
useful information. Based on our findings,
algorithmic trading programs are developed and
simulated.

5 Project Methodology Given the project uses both sentiment as well as


technical analysis.
1. The stock price data of the particular shall
be extracted.
Project Ideas - 2019-20

2. The sentiments and the news related to the


given company and the global economics
will be mined.
3. The given program shall be trained
accordingly giving each factor a specific
weightage and taken in to account the
technical trends and the current sentiments
regarding the company.
4. Additionally the indicators will help to show
us the overbuying and overselling of selling
of a stock also giving us the desired target
price more efficiently.

6 Literature Survey Reference : IEEE ACCESS


10.1109/ACCESS.2018.2886367
Guang Liu and Xiaojie Wang proposed a numerical-
based attention (NBA) method to predict stock prices.
In this method, the news is encoded to select the
numerical data. Benefits from this transforming,
noise is filtered and trend information of relevant
stocks is utilized. In order to evaluate our method,
three dual-source datasets source from the China
Security Index 300 (CSI300) and Standard & Poor’s
500 (S&P500) are build. Extensive experimental
results on these three datasets suggest that our NBA
is superior to previous models in dual-source stock
price prediction. The proposed method can
effectively exploit the complementarity between
news and numerical data in the stock market.

7 International connect
8 Project planning
1. Acquire stock and sentiment data.
(5-10 days)

2. Denoise the data using transformation methods


such as fourier transform and wavelet transform. (5
days)

3. Extracting features using Encoders.


(5-10 days)

4. Training data using various neural network model.


(15-30 days)

5. Testing model for predictive accuracy.


(15-30 days)
Project Ideas - 2019-20

6. Once the entire model is completely trained,


Implementing it in the real time to check the
accuracy of the model.(15-30 days)

9 Project usefulness/impact The project can be helpful for many individuals who
would like to invest their money in various stocks
giving them and a better in and out price. It can also
be used for short term trading purposes.

10 Project idea – own / external agency? Project is based upon own idea but it uses
references form many other resources. No
collaboration.

11 Project to Product Yes, the project can be converted to a working


Algorithmic trading strategy.

12 Resources needed Real time one minute and one day ticker data of
various company’s stock price as well as various
sentiment news regarding the domestic and
international financial markets.

13 Project cost The require cost will be not much for the project so
no funding required.

You might also like