Scribd
Upload
12 views11 pages

Stock Price Prediction

Uploaded by

singhsandeepabc6
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
12 views11 pages

Stock Price Prediction

Uploaded by

singhsandeepabc6
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

STOCK PRICE PREDICTION

USING MACHINE LEARNING

GROUP MEMBERS 7 Price Prediction


6

Afkar Najmain(09) 5
Anshika Gupta(16)
4
Devansh Rai(28)
Jatin Agrawal(37) 3

0
2002 2004 2008 2010 2012 2014 2016 2018 2020

Actual price Predict price


Objectiv
e:
Develop a predictive model to forecast stock market
prices using Keras LSTM (Long Short-Term Memory)
neural network.

Importance
Stock price prediction is a complex time-series
problem. This project uses Keras LSTM, a type of
neural network designed to handle sequential data,
to learn patterns from historical stock prices and
forecast future market trends.
FLOWCHART

DATA COLLECTION- DATA PREPROCESSING-


FETCHING HISTORICAL (Normalization,
STOCK(e.g;GOO Missing values,
G,TATAMOTORS. PRICE DATA
Feature scaling)
NS

TRAIN AND TEST MODEL ARCHITECTURE-


PREDICTION Keras LSTM Model
MODEL

DEPLOYINGMODEL OUPUT-CHARTS
AS WEB APP
Data Collection

Key
Source:
• Features
Collected historical stock data
using the yfinance python library
• Stock data includes:
open, high, low, close ,volume
• Time frame: eg; Jan 2010 to Dec
2020
• Data used for both training and
testing the model
Model Architecture:
Keras LSTM Model

Why to use LSTM?

• Using LSTM, time series forecasting models can predict future values
based on previous, sequential data and it is proven to be extremely
effective.

Method:
LSTM

• LSTM stands for Long Short Term Memory.


• It is a model that extends the memory of
Recurrent Neural Networks (RNN), which is
capable of learning long term dependencies.
• It is capable of capturing the patterns of both
long term such as a yearly pattern and short term
such as weekly or daily patterns.
LSTM Model
Model Training and testing

•Epochs: Set a reasonable number of epochs (e.g.,


20-50) to avoid overfitting.
•Batch Size: Common values are 32 or 64.
•Validation Set: Use a portion of the training data
for validation to track model performance during
training.
Results
•Comparison: Present a table or graph comparing the performance of the LSTM model based on evaluation
metrics.
•Visualization: Plot actual vs. predicted stock prices for the test dataset
Challenges
•Data Issues:
• Noisy and volatile nature of stock market
data
• Limited availability of high-quality labeled
data
•Model Limitations:
• Overfitting
• Computational complexity

Conclusion
•Summary: The Keras LSTM model demonstrates
potential in predicting stock market prices.
•Impact: Such models can assist investors in
making data-driven decisions, potentially leading to
better financial outcomes.
THANK YOU

You might also like