0% found this document useful (0 votes)
385 views27 pages

Stock Market Price Prediction

Uploaded by

kpsanjeev401
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
385 views27 pages

Stock Market Price Prediction

Uploaded by

kpsanjeev401
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 27

GREENFIELD CHENNAI INTERNATIONAL

SCHOOL
ARTIFICIAL INTELLIGENCE

PROJECT LOGBOOK (2024-2025)


AI Project Logbook

PROJECT NAME :- Stock Market Price Prediction using Artificial Intelligence and Big Data

SCHOOL NAME: GREENFIELD CHENNAI INTERNATIONAL SCHOOL, MADHAVARAM

YEAR/CLASS: 2024-2024 / XII

TEACHER NAME: HEMALATHA

TEACHER EMAIL: [email protected]

TEAM MEMBER NAMES :-

1. Robin

2. Avanthika

3. Nivethitha
Introduction

This document is your Project Logbook, and it will be where you record your ideas,
thoughts and answers as you work to solve a local problem using AI.

Make a copy of the document in your shared drive and work through it digitally with your
team. You can also print a copy of the document and submit a scanned copy once you
have completed the Project Logbook. Feel free to add pages and any other supporting
material to this document.
Team Roles

Who is in your team and what are their roles?

Role Role description Team Member Name

TO SCHEDULE AND ALLOCATE TASKS


LEADER AMONG TEAM MEMBERS FILLS
LOGBOOK AND ACT AS A Robin Binea Arun
LINK BETWEENTEACHER AND THE
TEAM MEMBERS.

INFORMATION COLLECTS QUESTIONS FROM TEAM, Nivethitha C


RESEARCHER FINDS ANSWERS AND FORWARD IT TO
TEAM LEADER.

TESTER WORKS WITH THE USERS TO TEST Avanthika


THE PROTOTYPE AND GET FEEDBACK
FROM THE USERS.
A. Project plan
The following table is a guide for your project plan.

Phase Task Planned Planned Planned Actual Actual end Actual Who is responsible Notes/Re
start date end date duration start date date duration marks
(hours, (hours,
minutes) minutes)
Preparing for the Coursework, 9/10/2024 10/10/2024 2 hrs 9/10/2024 10/10/2024 2 hrs Robin
project readings
Set up a team
folder 9/10/2024 10/10/2024 15 min 9/10/2024 10/10/20242 25 min Avanthika , Nivethitha
on a shared
drive
Problem 10/10/2024 11/10/2024 20 min 10/10/2024 11/10/2024 30 min Avanthika
Defining the Definition
problem
Research
issues in our 10/10/2024 11/10/2024 30 min 10/10/2024 11/10/2024 40 min Nivethitha
community

Team meeting
Discuss
issues and 10/10/2024 11/10/2024 20 min 10/10/2024 11/10/2024 20 min Robin
select an
issue for the
Project
Logbook

________________
Identify users 11/10/2024 12/10/2024 2 hrs 11/10/2024 12/10/2024 2 hrs Robin
Understanding
the users
Meeting with
users to
11/10/2024 12/10/2024 1 day 11/10/2024 12/10/2024 1 day Avanthika
observe them

Interview 11/10/2024 12/10/2024 2 hrs 11/10/2024 12/10/2024 2 hrs Nivethitha


with user (1)
____________________________________________
_
Interview

Brainstorming Team
meeting to
generate ideas 12/10/2024 13/10/2024 1 hrs 12/10/2024 13/10/2024 1 hrs All team members
for a solution

Complete
section 5 of the
12/10/2024 13/10/2024 2 hrs 12/10/2024 13/10/2024 2 hrs Avanthika
Project
Logbook
Team
Designing
our solution meeting to
design the 13/10/2024 14/10/2024 2 hrs 13/10/2024 14/10/2024 2 hrs Robin
Solution
Complete
section 6 of Nivethitha
13/10/2024 14/10/2024 8 hrs 13/10/2024 14/10/2024 10 hrs
the logbook

Collecting and Team meeting


preparing data
to 14/10/2024 15/10/2024 30 min14/10/2024 15/10/2024 30 min All Members
discuss data
requirements
Collecting and Data collection 1 hrs 1 hrs Avanthika
preparing data 14/10/2024 1510/2024 14/10/2024 15/10/2024
Prototyping
Data 1 hrs 1 hrs Nivethitha
preparation and 14/10/2024 15/10/2024 14/10/2024 15/10/2024
labeling

Complete 30 min 45 min Robin


Section 6 of the 14/10/2024 15/10/2024 14/10/2024 15/10/2024
Project
Logbook
Train your 4 hrs 4 hrs Robin
model with 15/10/2024 16/10/2024 15/10/2024 16/10/2024
Prototyping input dataset
Testing
Test your model 15-10-2024 16-1-2024 4 hrs15-10-2024 16-1-2024 4 hrs Nivethitha , Avanthika
and keep
training with
more data until
you think your
model is
accurate

Complete 15-10-2024 16-10-2024 1 hrs15-10-2024 16-1-2024 1 hrs Nivethitha , Avanthika


section 8 of the
Project
Logbook
Reflect on the 17-10-2024 20-10-2024 17-10-2024 20-1-2024 All members
project with
Completing your
the logbook Team
Complete 17-10-2024 20-1-2024 17-10-2024 20-1-2024 All members
sections 10 and
10 of the
Project
Logbook
Review your 17/10/2024 20/1/2024 17/10/2024 20/1/2024 All members
Project
logbook and
video
Submit your 21/10/2024 21/1/2024 21/10/2024 21/1/2024 All members
Submission
entries on IBM.
C. Communications plan

○ How will you plan to meet for discussion?

Online and Offline modes

○ How often will you come together to share your progress?

Weekly 2-3 times.

○ Who will set up online documents and ensure that everyone is contributing?

Robin

○ What tool will you use for communication?


Face to face, Google Drive, Whatsapp, Gmail

D. Team meeting minutes (create one for each meeting held)

Date of meeting : 15/10/2024 Who attended: Everyone

Purpose of meeting: To decide roles and responsibilities.

Topics discussed:
● Project Topic - Stock Market Price Prediction using Artificial Intelligence and Big Data

● Team Roles

● Problem Definition

● Communication plans
Problem Definition
E. List important local issues faced by your school or community
One of the important and tedious tasks in stock market price detection is that it
requires a huge time as well as a skilled mind. This paper proposes a smart and
efficient technique for detection of the varying price in the stock market which uses
Artificational Intelligence and Big Data.

Here are five common problems faced when using stock market price detection
methods:

1.Market Volatility: Stock prices can change rapidly due to market volatility,
making it difficult to obtain accurate or consistent price data. Sudden spikes or drops
can lead to misleading signals.

2.Data Quality: Inaccurate, outdated, or incomplete data can skew analysis.


Errors in data collection, transmission delays, or missing data points can
compromise the accuracy of price detection methods.

3.Algorithmic Bias: Many price detection methods rely on historical data, which
may introduce bias. If the algorithm overfits to past trends, it may fail to predict
future price movements effectively.

4.Latency Issues: In fast-paced markets, even minor delays in data processing


and transmission can lead to missed opportunities or incorrect trading decisions,
especially for high-frequency traders.

5.Impact of External Factors: Stock prices are influenced by news, economic


reports, political events, and other external factors that may not be captured in basic
price detection methods, leading to inaccurate predictions or missed events
impacting the market.

F. Which issues matter to you and why?


1.Overfitting to Historical Data: Some methods may overfit to past data, capturing noise rather
than true patterns. This can result in models that perform well on historical data but poorly on new
data.
2.Impact of Human Emotions: Stock markets are influenced by human behavior, which is often
irrational and unpredictable. Fear, greed, and speculation can lead to unexpected price
movements that are hard to model or predict accurately.
3.Complex Market Dynamics: Stock prices are influenced by numerous interconnected factors
such as interest rates, geopolitical events, and global market conditions. Simplified models may
not account for these complexities, leading to inaccurate predictions.
4.Lack of Real-time Data: For traders who need immediate updates, delayed or non-real-time data
can lead to outdated information, causing poor trading decisions based on incorrect prices.
G. Which issue will you focus on ?

Complex Market Dynamics: Stock prices are influenced by numerous interconnected factors such
as interest rates, geopolitical events, and global market conditions. Simplified models may not
account for these complexities, leading to inaccurate predictions.

H. Write your team’s problem statement

It was difficult to find the relevant market stock fluctuations and also the lack of Real-Time Data.

The Users
I. Who are the users and how are they affected by the problem?

Students

Counselor

Teachers

Counselor takes time to answer individual queries

J. What have you actually observed about the users and how the problem affects them?
1.Financial Losses: Inaccurate price predictions can lead to poor investment decisions, resulting in
significant financial losses for users who rely on these methods to time their trades.
2.Reduced Confidence in Trading: When users experience unexpected outcomes due to detection errors,
they may lose confidence in their trading strategies and become hesitant to make future investments.
3.Increased Stress and Anxiety: Frequent inaccuracies or unexpected market behavior can lead to stress
and anxiety for users, especially if they rely heavily on their investments for income or long-term goals.
4.Missed Opportunities: Delayed or incorrect price signals can cause users to miss profitable trading
opportunities or to enter positions too late, resulting in lost potential gains.
5.Higher Transaction Costs: Frequent or erratic trading, driven by unreliable price signals, can lead to
higher transaction fees, cutting into profits and affecting overall portfolio performance.
6.Over-reliance on Technology: Users may become overly dependent on automated systems and
algorithms, which can lead to complacency or reduced attention to fundamental analysis and other
important aspects of investing.
7.Emotional Decision-making: Frustration with detection errors may lead users to make impulsive or
emotional trading decisions, such as panic selling or overtrading, which can negatively impact their financial
health.
● Record your interview questions here as well as responses from users.

1.How often do you rely on stock market predictions for your investment decisions?

•Answer: “I rely on them daily for guidance.”

2.What is the biggest challenge you face when using stock market predictions?

•Answer: “Predictions are often too inconsistent.”

3.Do you feel that stock market predictions have improved your trading results?

•Answer: “Sometimes, but not always.”

4.How accurate do you think most stock market predictions are?

•Answer: “Usually, they’re about 50% right.”

5.How important is real-time data to your trading strategy?

•Answer: “It’s absolutely essential for me.”

6.Do you feel you have enough information to understand the factors affecting stock predictions?

•Answer: “No, I often feel in the dark.”

7.How much risk are you willing to take based on stock market predictions?

•Answer: “I’m willing to take moderate risks.”

8.Have you ever incurred losses due to relying on a stock market prediction?

•Answer: “Yes, unfortunately, I have.”

9.Do you think AI and machine learning have made stock predictions more reliable?

•Answer: “They help, but they’re not foolproof.”

10.What would make you trust stock market predictions more?

•Answer: “If they were consistently accurate over time.”


Empathy Map : Map what the users say, think, do and feel about the
problem

What our users are saying What our users thinking

They need a more reliable and faster Users often see stock market
means to predict accurate stocks predictions as helpful but unreliable,
viewing them as useful guidance but
acknowledging the risks of
inaccuracies and the need for
caution in decision-making.

What our users are doing How our users feel

Users are combining predictions with Users feel cautious yet hopeful using
personal research, diversifying stock market predictors, finding them
investments, and using caution by useful but often experiencing
not fully relying on predictions, frustration due to inaccuracies and
aiming to balance potential gains the unpredictability of the market.
with reduced risks.
e. What are the usual steps that users currently take related to the problem?

USER 1 :-

Conduct Independent Research: Users often supplement predictions with their own analysis,

including fundamental and technical research.

User 2 :-

Self-analysis and self-treatment

User 3 :-

Diversify Investments: To mitigate risks, they diversify their portfolios across different asset
classes and sectors.

PROBLEMS FACED DUE TO IT

a) More time required to identify stock price

b) Wrong Guess

c) Will affect financially

d) Will negatively affect developing business

e) Loss of money and time due to delay in starting prediction.


Brainstorming
b. Ideas

How might you use the power of AI/machine learning to solve the users’ problem by increasing
their knowledge or improving their skills?

AI Idea #1
Machine Learning Models: Utilize algorithms like Random Forests, Gradient
Boosting, or Neural Networks to analyze historical price data, trading volumes, and
other relevant features to predict future prices.
AI Idea #2
Sentiment Analysis: Analyze social media, news articles, and financial reports to
gauge market sentiment. Use Natural Language Processing (NLP) to quantify
sentiment and correlate it with price movements.
AI Idea #3
Technical Analysis: Develop a system that incorporates technical indicators (like
moving averages, RSI, MACD) to identify trends and potential reversal points in
stock prices.

AI Idea #4
Fundamental Analysis: Create a model that examines key financial metrics
(earnings reports, P/E ratios, etc.) to predict stock prices based on underlying
company performance.
AI Idea #5
Time Series Forecasting: Implement time series models like ARIMA or seasonal
decomposition to forecast stock prices based on historical patterns and seasonal
trends.
AI Idea #6
Market News Impact: Build a predictive model that assesses the impact of major
economic events, earnings announcements, or geopolitical news on stock prices,
allowing for real-time adjustments.

AI Idea #7
Portfolio Optimization Algorithms: Use techniques such as the Black-Litterman
model or mean-variance optimization to predict not only individual stock
movements but also the overall impact on a portfolio's value.

c. Priority Grid

Evaluate your five AI ideas based on value to users and ease of creation and implementation.
High value to users, easy to create High value to users, hard to create

Idea #3 Technical Analysis Idea #1 Machine Learning Models


Idea #4 Fundamental Analysis Idea #2 Sentiment Analysis

Low value to users, easy to create Low value to user , hard to create

Idea #5 Time Series Forecasting Idea #6 Market News Impact


Idea #7 Portfolio Optimization
Idea #6 Market News Impact Algorithms

Briefly summarize the idea for your solution in a few sentences and be sure to identify the tool that
you will use.
The prototype that we will make using the following ideas would utilize the data collected as well
as feedback from the public to improve its skill.
Design
What are the steps that users will now do using your AI solution
to address the problem?

With an AI-driven solution, users can take the following steps to improve their
approach to stock market predictions:

1.Access Real-time, AI-enhanced Data: Users will receive up-to-the-minute


insights with AI-enhanced predictions, providing more accurate and timely
information.
2.Customize Prediction Parameters: They can adjust prediction models based on
their risk tolerance, investment goals, and market preferences for personalized
results.

3.Receive Alerts for Key Market Changes: Users will get instant alerts on
significant market shifts or trends, allowing them to act quickly.

4.Leverage Sentiment Analysis: With AI analyzing market sentiment from news


and social media, users can make more informed decisions based on current
events.

5.Use Interactive Visualization Tools: Users can explore AI-generated


visualizations of market trends, helping them identify patterns and make data-driven
choices.
Data

a. What data will you need to train your Ai solution?


Historical Stock Price Data and Financial Statements.

b. Where or how will you source your data?

Where will the Do you have Ethical


data come from? Who owns the data? permission to use the considerations
Data needed data?
PAST RECORDS Public dataset YES SHOULD BE
Have
AUTHENTIC
IDENTIFICATION Public dataset YES SHOULD BE
Want /Need
ACCURATE
& AUTHENTIC

AI MODELS Public dataset YES SHOULD BE


Nice to have
ACCURATE
& AUTHENTIC
2. Prototype

a. Which AI tool(s) will you use to build your prototype Pictoblox,


Tensorflow with Keras

PictoBlox is coding education software that uses both graphical block-based coding and
Python programming. With a user-friendly interface and drag-and-drop functionality, it is the ideal
companion for setting the first step into the world of programming.

TensorFlow is an open-sourced end-to-end platform, a library for multiple machine


learning tasks.

Keras is a high-level neural network library that runs on top of TensorFlow. Both
provide high-level APIs used for easily building and training models, but Keras is more
user-friendly because it's built-in Python.

b. Which AI tool(s) will you use to build your solution?

Pictoblox, Tensorflow with Keras,

c. What decisions or outputs will your tool generate and what further
action needs to be taken after a decision is made?

Will do testing
Testing

Who are the users who tested the prototype?

Team members
students
counselor

List your observations of your users as they tested your solution.

The users showed an interest towards our solution.

Our solution was able to solve the issues that were discussed earlier.
Complete the user feedback grid

What works What needs to change

THE STOCK PREDICTOR


IDEAS. HARDWARE.

PROTOTYPE TO SOME EXTENT.


BETTER USER INTERFACE

MORE STORAGE

FASTER RESPONSE
Questions? Ideas

HOW ACCURATE ARE THE RESULTS? WHAT IF THE ACCURACY WILL BE IMPROVED AS THE
SYSTEM GAINS EXPERIENCE BECAUSEOF
ANN.
THERE IS A FUTURE ISSUE? IS THE MODEL
THE ALGORITHM CAN BE CHANGED TO
RESOLVE THE FUTURE ISSUE.
BIASED?
WE HAVE TRIED TO INCLUDE A DIVERSE TEAM
AS WELL AS TEST SUBJECT TO REDUCE AS
WELL AS DETECT BIASES.
Refining the prototype: Based on user testing, what needs to be acted on
now so that the prototype can be used?

1.Enhance User Interface: Simplify and improve the user interface for better
navigation and user experience, ensuring that it is intuitive and user-friendly.

2.Increase Data Accuracy: Improve the quality and accuracy of the data being fed
into the AI model to enhance prediction reliability and reduce errors.

3.Incorporate User Feedback : Actively incorporate feedback from user testing to


refine features, functionalities, and overall performance based on real user needs
and preferences.

4.Implement Real-time Capabilities: Ensure that the prototype can process and
analyze data in real-time to provide timely predictions and alerts to users.

5.Add Educational Resources: Provide tutorials or guides to help users


understand how to use the AI solution effectively, including how to interpret
predictions and data visualizations.

6.Develop Robust Testing Procedures: Establish a framework for ongoing testing


and validation of predictions to continually improve the model and adjust to market
changes.

7.Enhance Security Measures: Implement strong data security protocols to protect


user information and maintain trust in the platform.

What improvements can be made later?

It will be done once the A.I model gives live and more data from varied users to act
upon
Team collaboration

How did you actively work with others in your team


and with stakeholders ?
All members of our team were able to meet regularly and during
Dussehra vacation we have shifted to online mode. We have utilized
the facility of whatsapp, Meet and voice call etc. We have recorded
our activities in a shared drive. We have also collected feedback from
the stakeholders.
Individual learning reflection

Team Reflections

A good way to identify what you have learned is to ask yourself what surprised you during the project. List
the things that surprised you and any other thoughts you might have on issues in your local community.

Team member name: Robin

I would like to give my special thanks to my AI teacher as it was a pleasure to work on the project AI
STOCK PRICE PREDICTION. It has not only given me an opportunity to learn about the mechanism of
how stock prediction works but also helped us to know the importance of stocks and made us more aware
by learning on how to apply it in real life.

Team member name: Nivethitha

I would like to thank my teacher for giving us such a wonderful group project.
It was an interesting project to do. This project really helped me to learn the
meaning of a team and i got to experience how a team works. Also how the
STOCK MARKET works

Team member name: Avanthika

Sincere thanks to the teacher for giving us the opportunity to work on this project .
while working on this project i have learned many new and interesting things while
also gaining more knowledge about AI overall .
Video link

Enter the URL of your team video: Enter the password (if any):

You might also like