Stock Market Prediction Using Machine Learning

- In the finance world stock trading is one of the most important activities. Stock market
prediction is trying to determine the future value of a stock or other financial instrument traded
on a financial exchange. This paper explains the prediction of a stock using Machine Learning.
The technical and fundamental or time series analysis is used by most stockbrokers while
making stock predictions. The programming language used to predict the stock market using
machine learning is Python. In this paper, we propose a Machine Learning (ML) approach that
will be trained from the available stock data and gain intelligence, and then uses the acquired
knowledge for an accurate prediction. In this context this study uses a machine learning
technique called Support Vector Machine (SVM) to predict stock prices for the large and small
capitalizations and in the three different markets, employing prices with both daily and
up-to-the-minute frequencies.

Steps for Stock Market Prediction

Step 1: This step is important for downloading data from the net. We are predicting the financial
market value of any stock. So that the share value up to the closing date is download from the
site.
Step 2: In the next step the data value of any stock can be converted into the CSV file (Comma
Separate Value) so that it will easily load into the algorithm.

About Dataset
IBM is an American global innovation partnership settled in Armonk, New York, with tasks in
more than 171 nations. IBM creates and sells PC equipment, middleware, and programming,
and gives facilitating and counseling administrations in regions going from centralized server
PCs to nanotechnology. IBM is additionally a significant exploration association, holding the
record for most yearly U.S. licenses produced by a business (starting at 2020) for 28 continuous
years.

This Dataset is got and merged to do Real-Time Data Analysis. Stock Market Analysis is a
Complex Subject.

Data. Data Timeline: (06-04-2020) - (25-03-2022).

Total Rows: 216883

The data (last updated (26/03/2022) is presented in CSV format as follows: time, open, high,
low, close, and volume. Note that prices have been adjusted for dividends and splits.
Prediction column: Open

Data level: Minute

Aggregation function: Sum

Seasonality: 5

Seasonality is a characteristic of a time series in which the data experiences

regular and predictable changes that recur every calendar year. Any predictable
fluctuation or pattern that recurs or repeats over a one-year period is said to be
seasonal.
Model T7BK:
Model 2CND:
Forecast period : 500 (Duration of future predictions)