2. INTRODUCTION
• The stock (also capital stock) of
a corporation constitutes the equity stake of its
owners. It represents the residual assets of the
company that would be due to stockholders after
discharge of all senior claims such as secured and
unsecured debt.
• Stock market prediction is the act of trying to
determine the future value of a company stock or
other financial instrument traded on an exchange. The
successful prediction of a stock's future price could
yield significant profit.
3. Problem Statement
• The Stock Market prediction task is interesting
as well as divides researchers and academics
into two groups those who believe that we can
devise mechanisms to predict the market and
those who believe that the market is efficient
and whenever new information comes up the
market absorbs it by correcting itself, thus there
is no space for prediction.
5. June 2015, Noida
STOCK MARKET PREDICTION USING RIDGE AND RANDOM FOREST
REGRESSION
Shivank Chaudhary, Mrs. Akanksha Bhardwaj
Jaypee Institute of Information Technology, Noida
Abstract
As long as capital markets have existed,
investors have strived to gain edges in
predicting stock prices. In particular, use of
machine-learning techniques and quantitative
analysis to make stock price predictions has
become increasingly popular with time. In this
paper, we present a study to understand
trends of stock market prices and their
volatility using machine learning techniques,
such as ridge regression and forest regression.
We developed the mathematical model which
combines the above mentioned techniques to
calculate cross-validation score(CV) which
depicts nature of a company’s stock market.
Introduction
The stock (also capital stock) of a corporation
constitutes the equity stake of its owners. It
represents the residual assets of the company
that would be due to stockholders after discharge
of all senior claims such as secured and
unsecured debt. Stockholders’ equity cannot be
withdrawn from the company in a way that is
intended to be detrimental to the company’s
creditors. The stock of a corporation is
partitioned into shares, the total of which are
stated the time of business formation. Additional
shares may subsequently be authorized by the
existing shareholders and issued by the company.
In some jurisdictions, each share of stock has a
certain declared par value, which is a nominal
accounting value used to represent the equity on
the balance sheet of the corporation. In other
jurisdictions, however, shares of stock may be
issued without associated par value. A stock
market or equity market is the aggregation of
buyers and sellers(a loose network of economic
transactions, not a physical facility or discrete
entity) of stocks (also called shares). The novelty
of our project is that we developed an application
to find volatility of stock market prices of firms
using mathematical modelling of a cross between
machine learning techniques, mainly ridge and
random forest regression.
Motivation
The motivation of our project is:
• to determine whether the stock market
price of a firm remains extremely fluctuating
or stable
• decipher trends on real time change in
prices of stocks in companies
• determine characteristics and analysis of
stock price change in a given period of time
Conclusion
Directional movement of the stock market
(Will the stock close higher today than its
open?) is highly predictable given the
opening price today and the past days’
worth of open/close prices. In all of our
best models, we were able to predict the
directional movement of a stock with over
90% AUC.
This may come at a surprise to many
familiar with the stock market. The usual
response to hearing this result is to inquire
as to the viability of a trading strategy
focused on these patterns. Unfortunately,
the predictability of directional movement
does not translate to the certainty of
returns. Magnitude matters - trading
strategies focus on the magnitude of the
movement of a stock, not solely the
direction. While the direction is
predictable, the magnitude may not be.
Implementation methodology
We were inspired by the successes we’ve seen in algorithmic trading
and computer-assisted stock analysis. Several well-documented
effects we have read about online are the momentum effect and
regression to the mean. There has been a lot of research conducted
about the significance of the momentum effect in stock price
prediction. Lee and Swaminathan (2002) studied the relationship
between momentum and value trading strategies, while Grinblatt and
Moskowitz (2004) examined the effect of consistent positive past
returns on the link between past and expected returns. The wealth of
research in to price momentum made us interested in examining this
effect further and seeing how it could be applied to stock price
prediction models.
Acknowledgements
The large number of names and
organizations below indicates the
complexity of the project and the scope of
the entire research. While many
individuals assisted with a specific task, the
whole project benefited from their time,
effort, energy, and expertise:
•Jaypee Institute of Information
Technology
•Python Software Foundation
•Boston University