Scribd
Upload
47 views17 pages

Stock

This document discusses using data mining techniques to predict stock market prices. It proposes using 20 years of historical stock price data and machine learning algorithms like ARIMA to build models for predicting future prices. As an example, it applies this approach to Microsoft stock price data, preprocessing and cleaning the data to make it stationary before forecasting. The results show a 5.72% error rate for Microsoft, which is considered good. It suggests applying this approach to other tech companies for comparison and exploring new machine learning techniques to improve the models.

Uploaded by

Anuj Mehta
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
47 views17 pages

Stock

This document discusses using data mining techniques to predict stock market prices. It proposes using 20 years of historical stock price data and machine learning algorithms like ARIMA to build models for predicting future prices. As an example, it applies this approach to Microsoft stock price data, preprocessing and cleaning the data to make it stationary before forecasting. The results show a 5.72% error rate for Microsoft, which is considered good. It suggests applying this approach to other tech companies for comparison and exploring new machine learning techniques to improve the models.

Uploaded by

Anuj Mehta
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/ 17

Should

I Invest in
Stock Market ?
How To Be Rich in Stock Market: A Data-Mining Approach

Anuj Mehta
40415002716
CSE-II 5th Sem
Well..!!!
Should I BUY Ambani future
Reliance Ltd. Bad…
Shares????
Introduction
 Ability to predict direction of stock/index price
accurately is crucial for market dealers or investors to
maximize their profits.
 Data mining techniques have been successfully shown to
generate high forecasting accuracy of stock price
Movement
 Web is rich textual information resource such as
financial news even that is unmanageable to one. But
one can use this abundance textual information to get
datasets of various companies.
Goal
 This Project proposes a novel method for the prediction
of stock market closing price.

 It is an attempt to determine the stock price of


NASDAQ companies in upcoming years.
Architecture of Application
 This project aims at predicting stock market by using
previous 20 years stock price data in order to improve
quality of output.
 We are combining data mining time series analysis and
machine learning algorithms such as Autoregressive
integrated moving average model .
MICROSOFT STOCK PRICE ORIGINAL
Microsoft Cleaned Data using tsclean()
Exploring the data
we need stationary series to apply arima model to it for forecasting
Stationary data for arima model
Forecasting.…
Accuracy Check….
Error

Numerical Representation

5.72 % error is very


News Documents Preprocessing
less which is good

Prediction Module
 Applying to other Tech giants and compare
the results.
 Using new machine learning techniques to make
powerful models
 Determining the Stock market forecasts is always
been challenging work for business analysts.
 Thus, Project applies the data mining technology
of arima to stock price forecast and receives a
preferable result, which will provide the research
of the stock market development a new thought

You might also like