Title:

Stock Price prediction using Technical Analysis and Machine learning.

Abstract

We have many theories for stock market even some of them suggest we cant
predict stock price stock price are random and some say stock market is an untidy
place for predicting , there are no significant rules to estimate or predict the price of
share in the share market. For some historical stock prices are used to predict the
direction of future stock prices .We have many methods like technical analysis,
fundamental analysis, time series analysis and statistical analysis etc. are all used
to attempt to predict the price in the share market but none of these methods are
proved as a consistently acceptable prediction tool. Artificial Neural Network (ANN),
a field of Artificial Intelligence (AI), is a popular way to identify unknown and hidden
patterns in data which is suitable for share market prediction. For predicting of
share price using ANN, there are two modules, one is training session and other is
predicting price based on previously trained data. We used Back- propagation
algorithm for training session and Multilayer Feed-forward network as a network
model for predicting price. In this paper, we introduce a method which can predict
share market price using Back-propagation algorithm and Multilayer Feed-forward
network.

Need of Project:
From centuries in stock market mainly there are 3 major players Arbitrager, Hedger
and speculator. Now these speculators are transformed into trading firms, hedge
funds, brokers etc. This whole industry is trying to find out the model with which we
can predict the future price of trading instrument .This is human tendency to predict
future.

Background:
Fundamental Analysis:
Fundamental analysis is the physical study of a company in terms of its product
sales, manpower, quality, infrastructure etc. to understand it standing in the market
and thereby its profitability as an investment. The fundamental analysts believe
that the market is defined 90 percent by logical and 10 percent by physiological
factors. But, this analysis is not suitable for our study because the data it uses to
determine the intrinsic value of an asset does not change on daily basis and
therefore is not suitable for short-term basis. However, this analysis is suitable for
predicting the share market only in long-term basis.

Technical Analysis:
The technical analysis predicts the appropriate time to buy or sell a share. Technical
analysts use charts which contain technical data like price, volume, highest and
lowest prices per trading to predict future share movements. Price charts are used
to recognize trends. These trends are understood by supply and demand issues that
often have cyclical or some sort of noticeable patterns. To understand a company
and its profitability through its share prices in the market, some parameters can
guide an investor towards making a careful decision. These parameters are termed
Indicators and Oscillators. This is a very popular approach used to predict the
market. But the problem of this analysis is that the extraction of trading rules from
the study of charts is highly subjective, as a result different analysts extract
different trading rules studying the same charts. This analysis can be used to
predict the market price on daily basis but we will not use this approach because of
its subjective nature.
Machine Learning:
Methods Machine learning approach is attractive for artificial intelligence since it is
based on the principle of learning from training and experience. Models such as
ANNs are well suited for machine learning where connection weights adjusted to
improve the performance of a network
Material and methods:
Material:
The material (input or data set) required is the historical prices of the stock or
index .We can get it from Bloomberg terminal using rblpapi package(helps to
extract data from Bloomberg)
We can also get these data from quandl using quandl package and for technical
analysis as well as quantitative financial modelling we have quantmod package
(in dependencies we have to use xts library-to handle xts objects). We have
other packages that can handle financial application we may use those also
depending upon future requirement - fArma, fGarch, fOptions, fExoticOptions,
RMetrics, e1071, kernlab, nnet, caret, Metrics, PerformanceAnalytics,
quantmod, TTR, tseries, xts and AER.
For machine learning I am still reading research papers and books.
Methods:
we will use technical indicator as well NN to predict the price movements. To use NN
we have to split our data into train/test .with help of train data set we will build the
model and test that model on test data set ,if works fine we will implement that to
predict the future price of trading instrument .

Reference:
Financial application R package - http://computationalfinance.lsi.upc.edu/?
page_id=87
Research paper (University of Washington)
http://faculty.washington.edu/gyollin/docs/rFinancialData.pdf
http://quant.stackexchange.com/questions/14283/popular-r-packages-forquantitative-finance
http://www.rfortraders.com/
http://www.rinfinance.com/RinFinance2009/presentations/xts_quantmod_workshop.p
df
http://www.thertrader.com/
https://www.packtpub.com/big-data-and-business-intelligence/introduction-rquantitative-finance
http://gekkoquant.com/
http://datascienceassn.org/sites/default/files/A%20Novel%20Algorithmic%20Trading
%20Framework%20-%20Machine%20Learning%20for%20Portolio
%20Optimization.pdf

Search word ann machine learning for quantitative trading