(RM532P) AIML PROJECT Miriam Alice Sam - 2262822

Noel Shaji- 2262825

Keerthana Mahesh Kumar-
STOCK MARKET
2262837
Krishna Swaroop - 2262838

PREDICTION AND GRAPH Nidhin E- 2262843

Under the
Dr. Darshan S M
guidance
Mi ss i on Core Values
PLOTTING MODEL
Christ University is a nurturing ground for an
Vision
Excellence and Love of Fellow
Faith in GodBeings
| Moral|
Responsibility | Pursuit of
 CHRI
ST

FLOW OF PRESENTATION
1. IN TRODU CTION

2. OBJECTIVE

3. OUTCOME

4. RESEARCH PAPER EXAMPLE

5. FLOW OF THE PAPER

Excellence and
 CHRI
1. INTRODUCTION ST
• The stock market is constantly changing, influenced by
economic, political, and global events. Predicting stock
prices is challenging but can be very useful for decision-
making.
• This project focuses on building a Stock Market Prediction AI
Model using LSTM (Long Short-Term Memory). LSTM is a
type of neural network designed to handle time-series data
effectively.
• The model uses stock price data to predict future market
trends.
Excellence and
 CHRI
ST
OBJECTIVES
• Develop an LSTM-based AI model to
predict future stock prices using historical
data.
• Plot graphs to visualize predicted trends
alongside actual stock price data.
• Assist investors in making informed
decisions through clear and accurate trend
Excellence and
 CHRI
OUTCOME ST

Accurate Stock Price Predictions: The LSTM model effectively captures

temporal patterns, providing reliable forecasts of stock prices
•(Predicting stock market index using LSTM Hum Nath Bhandari a , Binod Rimal b,∗ , Nawa Raj Pokhrel c , Ramchandra Rimal d ,
Keshab R. Dahal e , Rajendra K.C. Khatri f)
Clear Trend Visualization: Graphs of predicted versus actual prices
enhance understanding of trends and support better investment
(A graph‑based CNN‑LSTM stock price prediction algorithm with leading indicators Jimmy Ming‑Tai Wu1 · Zhongcui Li1 · Norbert
•decisions. Herencsar2 · Bay Vo3 · Jerry Chun‑Wei Lin4)

Adaptability to Market Dynamics: The model performs well under

•varying market conditions and can be extended to other datasets for

Stock Market Analysis and Prediction Using LSTM: A Case Study on Technology Stocks Zhenglin Li 1, *, Hanyi Yu 2 , Jinxin Xu 3 ,
broader use​ Jihang Liu 4 and Yuhong Mo 5

Excellence and
 CHRI
ST

Excellence and
 CHRI
ST

Excellence and
 CHRI

6. CODE AND LSTM ST

• APPLICATION

Excellence and
 CHRI

6. CODE AND LSTM ST

• APPLICATION

Excellence and
 CHRI
ST
6. CODE AND LSTM
•
APPLICATION

Excellence and
1.
PROCESS OF IMPLEMENTATION
Model Selection and Validation

○ Validate LSTM's suitability for stock prediction by reviewing research on its ability to capture temporal dependencies and
long-term patterns.
2. Data Acquisition and Preprocessing

○ Collect comprehensive financial data from platforms like Kaggle and APIs. Clean the data, handle missing values,
engineer relevant features, and apply normalization or standardization.
3. Model Development and Training

○ Design and implement the LSTM model using frameworks like TensorFlow. Fine-tune hyperparameters and train the
model, using techniques like early stopping to prevent overfitting.
4. Evaluation, Optimization, and Deployment

○ Evaluate model performance using metrics like MSE and MAE. Optimize through iterative refinement and deploy the
final model, continuously monitoring and updating it with live data.

Excellence and
 RESEARCH PAPER
Name - Prediction of stock return by LSTM neural network

Author - Risheng Qiao, Weike Chen & Yongsheng Qiao

Publisher - Taylor & Francis Group

Findings -
LSTM Outperforms Traditional Models: The LSTM neural network delivers higher accuracy in stock return predictions compared to
traditional models like autoregressive models (AR), thanks to its ability to analyze sequential data and retain historical patterns.

RBM and LSTM Combination: Using Restricted Boltzmann Machine (RBM) for data preprocessing enhances the performance of the
LSTM model, enabling better feature extraction and improved prediction accuracy.

Excellence and
 Week1
Research on why the WEEKLY PROGRESS
LSTM approach is
best for stock
prediction taking Week 3
research papers in code development
account. and implimentation

Week2
Data collections Week 4
from various Implementation
platforms such as project completion
Github & Caggle,
Working on basic
code structure.

Excellence and
 REFERENCES

[1] W. Lu, J. Li, Y. Li, A. Sun, and J. Wang, "A CNN-LSTM-Based Model to Forecast Stock Prices," Complexity, vol. 2020, Article ID
6622927, 10 pages, 2020, doi: 10.1155/2020/6622927.

[2] A. Yadav, C. K. Jha, and A. Sharan, "Optimizing LSTM for time series prediction in Indian stock market," Procedia Computer
Science, vol. 167, pp. 2091-2100, 2020. Doi: 10.1016/j.procs.2020.03.257.

[3] M. Nabipour, P. Nayyeri, H. Jabani, A. Mosavi, E. Salwana, and S. S., "Machine Learning for Stock Market Prediction," Entropy, vol.
22, no. 8, p. 840, 2020. Doi: 10.3390/e22080840.

[4] H. N. Bhandari, B. Rimal, N. R. Pokhrel, R. Rimal, K. R. Dahal, and R. K. C. Khatri, "Predicting stock market index using LSTM,"
Machine Learning with Applications, vol. 2022, Article ID 100320, 2022, doi: 10.1016/j.mlwa.2022.100320.

[5] R. Qiao, W. Chen, and Y. Qiao, "Prediction of stock return by LSTM neural network," Applied Artificial Intelligence, vol. 36, no. 01,
Article ID e2151159, 2022, doi: 10.1080/08839514.2022.2151159.

Excellence and
 CHRI
ST

THANK YOU

Excellence and