0% found this document useful (0 votes)
7 views4 pages

SSRN Id3772584

This document discusses automated stock trading using machine learning. It proposes a model that extracts features from sentiment analysis of tweets as well as time series data like price and volume. The model uses techniques like natural language processing, Naive Bayes classification, time series prediction, autoregression, and ARIMA statistical modeling to predict stock price movements. It implements data pre-processing, feature extraction from tweets, and sentiment analysis to classify sentiments and predict stock prices. The goal is to use machine learning coupled with fundamentals and technical analysis to yield satisfactory results for stock market prediction.

Uploaded by

ANUP MUNDE
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)
7 views4 pages

SSRN Id3772584

This document discusses automated stock trading using machine learning. It proposes a model that extracts features from sentiment analysis of tweets as well as time series data like price and volume. The model uses techniques like natural language processing, Naive Bayes classification, time series prediction, autoregression, and ARIMA statistical modeling to predict stock price movements. It implements data pre-processing, feature extraction from tweets, and sentiment analysis to classify sentiments and predict stock prices. The goal is to use machine learning coupled with fundamentals and technical analysis to yield satisfactory results for stock market prediction.

Uploaded by

ANUP MUNDE
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/ 4

AUTOMATED STOCK TRADING USING MACHINE

LEARNING
Anup Munde
Ashwin Jadhav
Pune Institute Of Computer technology,
Pune, India. Pune Institute Of Computer technology,
Pune, India.
manupmunde@gmail.com
ashwinjadhav099@gmail.com
Harshal Kaute Ajay Gosavi
Pune Institute Of Computer technology, Pune Institute Of Computer technology,
Pune, India Pune, India.
harshal.kaute2411@gmail.com ajaygosavi1243@gmail.com

Abstract—Predicting stock market movements is a well-known check the actual movement of the market is essential. Many
problem of interest. Now-a- days social media is perfectly
times market movement can’t be predicted due to pseudo
representing the public sentiment and opinion about current
events. Especially, Twitter has attracted a lot of attention from force and it can’t sustain more or less than the upper and
researchers for studying the public sentiments. Stock market lower circuit. So here investors should be aware of
prediction on the basis of public sentiments expressed on retracement of market movement at any time.
Twitter has been an intriguing field of research. The approach
through sentimental analysis is to observe how well the changes 2.In the proposed model, we extract features not only from
in stock prices i.e. the rise and fall are correlated to the opinion
of people that are expressed by them on Twitter. Sentimental sentimental analysis results mining from Twitter, but also from
analysis helps in analyzing the public sentiments on Twitter, time series data source (price and volume) .
this approach is our approach through using make of
sentimental analysis. Another approach in the same topic of our 3. Using the historical data of a stock to analyse how the
project is using technical analysis. We model the stock price movement of the stock has been in the last one year it becomes
movement as a function of these input features and solve it as a
regression problem in a multiple kernel learning regression
easy to predict the future movement of the stock.
framework. The machine learning coupled with fundamental
and/ or technical analysis also yields satisfactory results for
stock market prediction. We also evaluated the model for III. ALGORITHM AND METHODOLOGIES
taking buy-sell decision at the end of day which is also known as
intraday trading.
1. NATURAL LANGUAGE PROCESSING

Keywords—Machine learning, Stock price, Stock market,


Natural language processing (NLP) may be a subfield of
Supportvector machine, Natural language processing
linguistics, computing , information engineering, and AI
concerned with the interactions between computers and human
(natural) languages, especially the way to program computers
to process and analyze large amounts of tongue data.
I. INTRODUCTION Challenges in tongue processing frequently involve speech
recognition, tongue understanding, and tongue generation.
A correct prediction of stocks can lead to huge profits for the 2. NAIYE BAYES ALGORITHM
seller and the broker. Frequently, it is brought out that
prediction is chaotic rather than random, which means it can Naive Bayes classifier uses applied mathematics to classify
be predicted by carefully analyzing the history of respective data. Naive Bayes classifier algorithms make use of Bayes'
stock market. Machine learning is an efficient way to theorem . The key insight of Bayes' theorem is that the
represent such processes. It predicts a market value close to probability of an event can be adjusted as new data is
the tangible value, thereby increasing the accuracy. introduced.What makes a naive Bayes classifier naive is its
Introduction of machine learning to the area of stock assumption that each one attributes of a knowledge point into
prediction has appealed to many researches because of its account are independent of every other. A classifier sorting
efficient and accurate measurements. In this project, fruits into apples and oranges would know that apples are red,
supervised machine learning is employed on a dataset round and are a certain size, but would not assume all these
obtained from Yahoo Finance. things at once. Oranges are round too, after all.

3. TIME SERIES PREDICTION


Time series analysis comprises methods for analyzing statistic
II. METHODOLOGY
1. Output of sentimental analysis can’t be the only deciding data so as to extract meaningful statistics and other
characteristics of the info . Time series forecasting is that the
factor in predicting process. Use of technical analysis to
use of a model to predict future values supported previously

Electronic copy available at: https://ssrn.com/abstract=3772584


observed values. While multivariate analysis is usually
employed in such how on test theories that the present values 2. SENTIMENTAL ANALYSIS
of 1 or more independent statistic affect the present value of
once more series, this sort of study of your time series isn't
called "time series analysis", which focuses on comparing
values of one statistic or multiple dependent time series at
different points in time. Interrupted statistic analysis is that the
analysis of interventions on one statistic ..
4. AUTO REGRESSION

Autoregression is basically a time series model that uses


observations from previous time steps or from the past data as
input to a regression of y on x to predict the worth at the
following time step. It is a simple concept that may end up in
accurate forecasts on a spread of your time series problems
which is a great way to predict the future price of a company's
stock.
5. ARIMA FROM STATS MODEL

Auto regressive integrated moving average(ARIMA) is


statistical model for time series prediction. The standard
notation for the model is ARIMA(p,d,q) where p is total lag
observations also called lag order, d is number of times that the
raw observations are differenced also called degree of Fig 2: Sentimental analysis
differencing, and q is size of moving average window. Model
predicts future state by checking difference between values in
time series instead of actual stock value. V. IMPLEMENTATION TECHNIQUES

1.Raw data pre-processing component:

IV. IMPLEMENTATION It takes content of news and comments as input, and


also takes historic price and volume data as raw data
for further process the content of tweets require
1. TECHNICAL ANALYSIS cleaning which helps us in creating the sentiment
analysis.

2. Feature extraction component:

It breaks down each and every word in the fetched


tweets and compares it with bag of words, if that
word exists in bag of words then it assigns it labels
from that respective bag of words.

3. Sentiment analysis component:

It analyzes the overall sentiments (objective,


subjective, positive, negative), a threshold value for
overall sentiments is set to classify each sentiment.
The output of process will be the actual percentage of
positive and negative sentiment from the fetched data.

4. Technical analysis component:


It formulates different indicators based on price and
volume. These indicators generate signals movement
of market. Then we combine outputs of each signal
using simple combination or using Neural Network
combination. The trend of market is predicted as
output of technical analysis.

Electronic copy available at: https://ssrn.com/abstract=3772584


VI. CONCLUSION [7] “Quantitative Analysis of Stock Market Prediction
for Accurate Investment Decisions in Future”, Surbhi
Sharma, Baijnath Kaushik, Journal of Artificial
The proposed system will help beginner traders as a decision
Intelligence, ISSN 1994-5450, 2018.
support tool and help them take decisions accordingly. Baijnath Kaushik, Journal of Artificial Intelligence,
Collective analysis of news regarding market have been made ISSN 1994-5450, 2018. Baijnath Kaushik, Journal of
easy using machine learning algorithms. Artificial Intelligence, ISSN 1994-5450, 2018.

VII. REFERENCES

[1] “Approaches, Tools and Applications for Sentiment


Analysis Implementation”, Alessia D’Andrea, Fernando Ferri,
Patrizia Grifoni, Tiziana Guzzo, International Journal of
Computer Applications (0975 – 8887) Volume 125 – No.3,
September 2015.
[2] “Stock Market Classification Model Using Sentiment
Analysis on Twitter Based on Hybrid Naive Bayes
Classifiers”, Ghaith Abdulsattar A.Jabbar Alkubaisi, Siti
Sakira Kamaruddin & Husniza Husni, Computer and
Information Science; Vol. 11, No. 1; 2018, ISSN 1913-8989 E
ISSN 1913-8997
[3] “Stocks Market Prediction Using Support Vector
Machine”, Zhen Hu, Jie Zhu, and Ken Tse, 2013 6th
International Conference on Information Management,
Innovation Management and Industrial Engineering
[4] “Sentiment Analysis in Twitter using Machine Learning
Techniques”, Neethu M S, Rajasree R, 4th ICCCNT 2013, July
4 - 6, 2013, Tiruchengode, India.
[5] “The Integration of Fundamental and Technical Analysis in
Predicting the Stock Price”, Isnaini Nuzula Agustin, Volume
18, Nomor 2, Mei 2019, pp 93-102. Studi Manajemen,
Fakultas Ekonomi, Universitas Kristen Maranatha. ISSN 1411-
9293 | e-ISSN 2579-4094.
[6] “STOCK MARKET FORECASTING TECHNIQUES:
LITERATURE SURVEY”, Vivek Rajput, Sarika Bobde,
International Journal of Computer Science and Mobile
Computing, Vol.5 Issue.6, June- 2016.

Electronic copy available at: https://ssrn.com/abstract=3772584


Electronic copy available at: https://ssrn.com/abstract=3772584

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy