STOCK PRICE PREDICTION

USING MACHINE LEARNING

SUBMITTED BY:
ANJALI
SAMYUKTHA
RONIT SINGH
KARTHIK
GAURAV

SUBMITTED TO:PRATHYUSHA
TURLAPATI MAM
ABSTRACT:
• The main aim of the project is to predict the stock price closing value for
a particular company by using machine learning Techniques. Machine
Learning algorithms have been used to devise new techniques to build
prediction models that can forecast the prices of stock and tell about the
market trend with good accuracy. Many prediction models have been
proposes to incorporate all the major factors affecting the price of stocks
one of the famous technique is Long short-term memory (LSTM)
• For training and predicting the stock price. To build the stock price
prediction model, we will using Real Time Google Dataset which
consists last years data and we are using Goggle Colab as a software for
Making the prediction.
OBJECTIVES
Aim of the Project:
The aim of the project is to build the stock price prediction model
which can predict the stock price for future based on the given
dataset.

Scope of the project:

Prediction of stock price using Machine Learning will be useful for
new investors to invest in stock market based on the various factors.
INTRODUCTION:

• Stock market prediction is a major exertion in the field of finance and

establishing businesses.
• Stock market is totally uncertain as the prices of stocks keep fluctuating
on a daily basis because of numerous factors that influence like physical
factors vs psychological factors,rational and irrational behavior etc.
• All these aspects combine to make share prices volatile and very difficult
to predict with a high degree of accuracy.
• The solution to predict the stock price is Machine Learning. Machine
Learning algorithms have been used to devise new techniques to build
prediction models that can forecast the prices of stock and tell about the
market trend with good accuracy.
DESIGN AND METHODOLOGIES

• MODULE 1: Downloading Dataset and Pre-processing the Dataset

• MODULE 2: Splittting the Dataset for Training and Testing
• MODULE 2: Applying the LSTM Technique for the Model
• MODULE 4: Evaluating the prediction Accuracy and Getting the
output
IMPLEMENTATI
ON

• ARCHITECTURE DIAGRAM
• DATA FLOW DIAGRAM
• SEQUENCE DIAGRAM
• COLLABORATION DIAGRAM
• ER DIAGRAM
ARCHITECTURE DIAGRAM
Data Preprocessing
Historical Stock
Data
Feature selection

Training Data Testing Data

Create Model Train the Model Test the Model

LSTM

Evaluate prediction
Adjust Parameters Accuracy
DATA FLOW DIAGRAM
Downloading The Google Dataset

PRE-PROCESS THE
DATA
SPLITTING THE DATASET
FOR TRAINING AND TESTED

APPLYING LSTM
TECHNIQUE

TRAINING THE DATA

TESTING THE DATA

GET THE OUTPUT

ER-DIAGRAM
DATE

VOLUME OPEN

GOOGLE
DATASET

HIGH
CLOSE

LOW
INPUT AND OUTPUT
TESTING DATASET
INPUT AND OUTPUT
TRAINING DATASET
CONCLUSION

• In this project we used LSTM technique for Training the model and
we have taken Google dataset and we trained our model.

• We split the data into 70% for Testing and 30% for Training.

• We Predicted the Stock Price closing for the dataset.

• We have achieved 80% of Stock price prediction for the dataset .

FUTURE ENHANCEMENT

• As we have predicted the Stock price for Google dataset by using LSMT
similarly the technique is used for any kind of dataset to make
predictions.
• LSMT is not only used in stock price prediction it is used in many other
field in future LSMT is used to analysis the satellite hand writing
recognation.
• LSMT can also be used for real time speech to text conversion etc.
THANK YOU