0th Review2

You might also like

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 17

Dr.

Mahalingam College of Engineering & Technology


Department of Artificial Intelligence & Data Science
19ADPN6401 – Mini Project
Zeroth Review
Team Number: 22BAD013
Domain: Data Science

Title: Stock Market Prediction Using Lstm and Bert

Guide :Dr.M.Balakrishnan
Mrs.S.Thelungu Lakshmi

Team Members: S.Prienga (727622BAD074)


K.Sri vaishnavi (727622BAD054)
N.Srinivasan (727622BAD068)

11/03/2023 Cancer Prediction Web application


Contents
• Problem description(domain)
• Findings of Literature survey [ minimum 12 papers]
• What is stock market
• Existing System Block Diagram
• Drawback
• Proposed System Block Diagram
• List of Modules and detailed Module description
• Results
• Conclusion
• Snapshots
• Online Course/Contest / Publication Details
• References [minimum 13 papers including base
paper]

13/03/2023 Cancer Prediction Web application 1


Problem Statement
• The combination of LSTM and BERT models, has shown promising results in
predicting stock market prices.By leveraging the strengths of both models,
the hybrid approach improves the accuracy and robustness
of the predictions

13/03/2023 Cohort retention analysis 2


What is stock market ?
The stock market is a venue for people to buy and sell their stock. this background
involves risk

13/03/2023 Cohort retention analysis 2


Types of stock market:-
• Scalping-Trade for 5 to 10 mins
• Intraday-Trade for 9.15 to 3.30 mins
• Swing Trading-Trade for 1 to 4 weeks
• Postioning-trade for 4 month to 1 year

13/03/2023 Cohort retention analysis 2


HISTORY OF STOCK MARKET
PREDICTION
• 19TH and early 20th century
• Dow theory(1990’s)
• 1950-1980(Computer technology allowed in stock market prediction)
• 1990 – 2000(Internet has been helpful for private buyers)

07/17/2024 Sign Language Recognition using Depth Data 6


Literature Identified and Findings

13/03/2023 Cohort retention analysis 2


1.PREDICTION METHODS
• Fundamental analysis:
Company profiles,Industry prospects,Political
factor,economic factors,news,social media.
• Technical analysis:
K-Line,moving average,relative strength

07/17/2024 Sign Language Recognition using Depth Data 8


2.VARIOUS MACHINE LEARNING METHODS

• KNN
• Naive Bayesian classifier
• Support vector machine(s v m)
• ARIMA(Auto regressive integrated moving average)
• Random forest

07/17/2024 Sign Language Recognition using Depth Data 9


3.DEEP LEARNING METHODS
• Recurrent neural network
• Long short term memory
• Graph neural network

07/17/2024 Sign Language Recognition using Depth Data 10


4.BERT
The BERT (Bidirectional Encoder Representations from Transformers)
model is a transformer-based model that utilizes a bidirectional
approach to learn contextual representations of words. It consists of
multiple transformer layers that enable the model to capture the
dependencies between words in both directions.

07/17/2024 Sign Language Recognition using Depth Data 11


5.LSTM
Long Short-Term Memory (LSTM) is a type of recurrent neural network
(RNN) that is commonly used for time series forecasting, including stock
market price prediction. The LSTM model has the ability to capture
long-term dependencies in the data, making it suitable for analyzing
and predicting stock market trends.

07/17/2024 Sign Language Recognition using Depth Data 12


BENEFITS OF AI IN STOCK PRICE PREDICTION

• Accuracy
• Faster analysis
• Risk management
• Personalized recommendations
• Cost savings

07/17/2024 Sign Language Recognition using Depth Data 13


Data Set
The data set for stock market prediction using lstm and bert is collected from an
online dataset platform called Kaggle, yahoo finanace , FINRA - Market data
center , Dow jones industrial Averages

13/03/2023 Cohort retention analysis 2


Requirements
• Datasets of real stock market.
• Python 3 or above.
• Sypder 5.0 version or above.
• Google collabratory.
• Laptop or pc over intel i5 11th gen processor for fast processing.

13/03/2023 Cohort retention analysis 2


Weekly Plan
Week 1 = Data collection for cohort retention analysis

Week 2 = Data preparation for analysis

Week 3 = Defining cohorts and calculate retention rate

Week 4 = Visualizing the formatted data

Week 5 = Result analysis and documentation

13/03/2023 Cohort retention analysis 2


Thank You

13/03/2023 Cancer Prediction Web application

You might also like