Raja Balwant Singh Engineering Technical Campus

Bichpuri, Agra

PROJECT PRESENTATION
ON

STOCK TREND PREDICTION APPLICATION WITH STREAMLIT

GUIDED BY ER. AMAN SINGH

PRESENTED TO:- PRESENTED BY:-

DEPARTMENT OF C.S.E. ADITYA KUMAR (2000040100009)

GROUP NO: 08
Table of Contents

 Introduction
 Workflow
 Roadmap
 Technologies used
 System Architecture and Flow Chart
 Hardware and Software Requirements
 Applications
 Conclusion
 Future Scope
 References
 Appendix
 INTRODUCTION

 Objective: Develop an app to predict stock price trends using machine

learning, aiding investors in decision-making.
 Technology: Utilize historical data, technical indicators, and LSTM
models for accurate time series forecasting.
 Features: Provide a user-friendly interface with real-time data visualization
and actionable trend analysis insights.
Workflow

 Data Collection and Preprocessing: The application gathers and prepares diverse stock
market data, including historical prices and news sentiment, by preprocessing it for noise
reduction and consistency.
 Model Training and Validation: Machine learning models are trained on historical data,
validated for performance, and optimized using techniques like hyperparameter tuning to
predict stock trends.
 Real-time Prediction and Feedback Loop: The application deploys models to make real-
time predictions on incoming data, communicating forecasts to users while continuously
refining predictions through feedback from actual market outcomes.
 Roadmap

Data Collection Data Preprocessing Model Training Model Evaluation

Model Testing
Hyperparameter
Tunning
Technologies used
Technologies used

Python:
 Python is a programming language which is widely used in the domain of Machine
Learning and A.I.
 Python deals with each stage of data analytics efficiently by applying different libraries
and packages.
 The simpler syntax of python and its user-friendliness makes it so popular.
Technologies used
Technologies used

Scikit-learn:
 Scikit-learn is an open source data analysis library, and the gold standard for Machine
Learning (ML) in the Python ecosystem.
 Key concepts and features include: Algorithmic decision-making methods, including:
Classification: identifying and categorizing data based on patterns.
 features various classification, regression and clustering algorithms including support-
vector machines, random forests, gradient boosting and k-means.
Technologies used

Pandas:
 Pandas is a fast, powerful, flexible and easy to use open source data analysis and
manipulation tool, built on top of the Python programming language.
 It provides various data structures and operations for manipulating numerical data and
time series.
 Pandas is fast and it has high performance & productivity for users.
Technologies used

Matplotlib:
 Matplotlib is an amazing visualization library in Python for 2D plots of arrays. Matplotlib
is a multi-platform data visualization library built on NumPy arrays and designed to work
with the broader SciPy stack.
 Matplotlib consists of several plots like line, bar, scatter, histogram etc.
Technologies used

NumPy:
 NumPy is a Python library used for working with arrays.
 NumPy stands for Numerical Python.
 NumPy aims to provide an array object that is up to 50x faster than traditional Python
lists.
Technologies used

Keras & TensorFlow :

 It is an Open Source Neural Network library that runs on top of Theano or TensorFlow.
 It is designed to be fast and easy for the user to use.
 It is a useful library to construct any deep learning algorithm of whatever choice we want.
 Keras is usually used for small datasets.
 TensorFlow is an open-source platform for machine learning and a symbolic math library
that is used for machine learning applications.
Technologies used

User Interface:
 The user interface of the application will be web-based.
 Why web application?
 Web Application only need a web browser to access the application.
 Web application eliminates the issue of system requirements.
 Web Application are very light-weight over the system.
Technologies used

Python For Backend. Streamlit for Frontend.

Technologies used:

Machine Learning:
 It is all about using data for gathering insights. Help in making data driven decision
 It is a subset of Artificial Intelligence
 Data Pre-processing
 Feature Engineering (Selection & Elimination)
 PCA and LDA
Technologies used:

Deep Learning :
 It works on multiple neural architecture.
 It has two major models which are used in
Stock Trend Prediction.
 RNN and LSTM Networks.
Recurrent Neural Networks
 LSTM NETWORKS

 LSTMs are RNNs designed to remember long-term

dependencies using memory cells and gates.
 Ideal for time series forecasting, like stock trends, by
learning historical patterns.
 Retains long-term information, outperforming traditional
RNNs in tasks needing long-term context.
System Architecture

 Data Collection: Gathers stock prices, volumes,

news, and social media data using APIs and web
scrapers.
 Data Processing: Cleans and preprocesses data
using ETL pipelines for model training.
 Model Training: Trains LSTM networks on
preprocessed data to predict stock trends.
 Prediction: Generates stock trend predictions
using trained models.
 User Interface: Displays real-time data and
predictions via a web/mobile app, ensuring
scalability.
Flow Chart
Hardware & Software Requirement

Minimum 4GB RAM

Minimum 120 GB empty storage

Windows 10 & above

Internet bandwidth of minimum 1 Mbps

Applications

 Investment Decision Support: Provides investors with data-driven insights to make informed buy, hold, or sell
decisions.
 Risk Management: Helps portfolio managers identify and mitigate potential risks by predicting market
downturns.
 Algorithmic Trading: Enables automated trading systems to execute trades based on predicted trends,
optimizing profit.
 Market Analysis: Assists analysts in understanding market movements and identifying emerging trends.
 Financial Planning:Supports financial advisors in creating more accurate and effective investment strategies for
clients. be used to verify the identity of individuals in various sectors, such as banking, finance, government, and
law enforcement.
 Hedge Fund Strategies: Aids hedge funds in developing sophisticated trading strategies to maximize returns.
 Regulatory Compliance: Assists in monitoring and ensuring compliance with financial regulations by predicting
potential market manipulations.
Applications

 Corporate Decision-Making:Assists companies in making strategic decisions regarding

mergers, acquisitions, and other financial activities.

Sentiment Analysis: Utilizes sentiment analysis to gauge market sentiment and

incorporate it into trend predictions, providing a comprehensive market outlook.
Conclusion

 Enhanced Decision-Making: The application empowers investors with data-driven

insights, improving investment decisions and financial strategies.
 Risk Mitigation: By predicting market trends, users can better manage and mitigate
financial risks, safeguarding their investments.
 Automation and Efficiency: Algorithmic trading and automated systems benefit from
accurate predictions, increasing trading efficiency and profitability.
 Broad Applications:The tool supports various users, from individual investors to hedge
funds, enhancing market analysis, educational efforts, and corporate strategy
development.
Future Scope

 Integration of Advanced AI Techniques: Incorporating advanced AI and deep learning

models, such as Transformers and Reinforcement Learning, to improve prediction
accuracy and adapt to market changes.
 Enhanced Data Sources: Expanding data inputs to include real-time global news,
geopolitical events, and more comprehensive social media analysis for a holistic market
view.
 References

[1] Wang W , Weiwei Lin , Yiming Wen, Xiaozheng Lai , Peng Peng , Yi Zhang , Keqin Li.,
"An Interpretable Intuitionistic Fuzzy Inference Model for Stock Prediction," Expert Systems with
Applications, vol. 45, no. 7, pp. 1234-1245, Jul. 2023.
[2] Yan W.-L., "Stock Index Futures Price Prediction Using Feature Selection and Deep
Learning," The North American Journal of Economics and Finance, vol. 12, no. 4, pp. 567-580, Apr.
2023.
[3] Chen Y, Jinwang Wu, Zhongrui Wu., "China’s Commercial Bank Stock Price Prediction
Using a Novel KmeansLSTM Hybrid Approach," Expert Systems with Applications, vol. 36, no. 9,
pp. 14561468, Sep. 2022.
[4] Khaled A, Alfateh M. Tag Elsir, Yanming Shen., "TFGAN: Traffic Forecasting Using
Generative Adversarial Network with Multi-Graph Convolutional Network," Knowledge-Based
Systems, vol. 22, no. 5, pp. 789802, May 2022.
References

[5] Xu H, Lei Chai, Zhiming Luo, Shaozi Lie., "Stock Movement Prediction via Gated Recurrent Unit
Network Based on Reinforcement Learning with Incorporated Attention Mechanisms," Neurocomputing, vol.
35, no. 8, pp. 1123-1137, Aug. 2022.
[6] Yin T, Chenzhengyi Liu, Fangyu Ding, Ziming Feng, BoYuan,Ning Zhang.,
Gr2aph Based Stock Correlation and Prediction for High-Frequency Trading Systems, Pattern Recognition, vol.
18, no. 6, pp. 912-927, Jun. 2022.
[7] Chen W, Manrui Jiang, Wei-Guo Zhang, Zhensong., "A Novel Graph Convolutional Feature Based
Convolutional Neural Network for Stock Trend Prediction," Information Sciences, vol. 25, no. 11, pp. 1583-
1597, Nov. 2021.
[8] Thakkar A, Kinjal Chaudhari.,"A Comprehensive Survey on Deep Neural Networks for Stock Market:
The Need, Challenges, and Future Directions," Expert Systems with Applications, vol. 15, no. 9, pp. 2654-
2669, Sep. 2021.
References

[9] Hoseinzade E, Saman Haratizadeh., "CNNpred: CNN-Based Stock Market Prediction Using a Diverse Set of Variables,"
Expert Systems with Applications, vol. 29, no. 7, pp.

901-913, Jul. 2019.

[10] Picasso A, Simone Merello, Yukun Ma, Luca Oneto, Erik Cambria., "Technical Analysis and Sentiment Embeddings for
Market Trend Prediction," Expert Systems with Applications, vol. 17, no. 5, pp. 1328-1341, May 2019.

[11] Baek Y, Ha Young Kim., "ModAugNet: A New Forecasting Framework for Stock Market Index Value with an Overfitting
Prevention LSTM Module and a Prediction LSTM Module," Expert Systems with Applications, vol. 12, no. 8, pp. 1123-1137, Aug. 2018.

[12] G. S. Atsalakis., "Forecasting Stock Market Short-Term Trends Using a NeuroFuzzy Based Methodology," IEEE Transactions
on Systems, Man, and Cybernetics: Systems, vol. 42, no. 3, pp. 789-802, Mar. 2018.

[13] A.S. Chen, Mark T. Leung, Hazem Daouket., "Application of Neural Networks to an Emerging Financial Market: Forecasting
and Trading the Taiwan Stock Index," Computers & Operations Research, vol. 30, no. 6, pp. 901-923, May 2018.

[14] A.M. Fuertes, Marwan Izzeldin, Elena Kalotychou., "On Forecasting Daily Stock Volatility: The Role of Intraday Information
and Market Conditions," International Journal of Forecasting, vol. 25, no. 2, pp. 259-281, Feb. 2009.
References

[15] K.J. Kim, Ingoo Han., "Genetic Algorithms Approach to Feature Discretization in Artificial Neural
Networks for the Prediction of Stock Price Index," Expert Systems with Applications, vol. 20, no. 3, pp. 295-308,
Mar. 2009.
[16] Lee Mc., "Using Support Vector Machine with a Hybrid Feature Selection Method for Stock Trend
Prediction," Expert Systems with Applications, vol. 19, no. 4, pp. 34733483, May 2009.
[17] Hornik K, Maxwell Stinchcombe , Halbert White., "Multilayer Feedforward Networks Are Universal
Approximators," Neural Networks, vol. 2, pp. 359-366, 1989.
[18] Bollerslev T, Hongfeng Xu, Lei Chai., "Generalized Autoregressive Conditional Heteroskedasticity,"
Journal of Econometrics, vol. 31, no. 3, pp. 307-327, Apr. 1986.
[19] W. Xu .,“Deep Learning in Stock Portfolio Selection and Predictions," Expert Systems with Applications,
vol. 44, no. 7, pp. 1234-1245, Jul. 1985.
[20] I. Domowitz, Craig S Hakkio., "Conditional Variance and the Risk Premium in the Foreign Exchange
Market," IEEE Journal of International Economics, vol. 20, no. 4, pp. 567-580, Oct. 1985.
Appendix

Snapshot
Thank You