See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/340809604

Digital Signal Processing for Predicting Stock Prices in Financial market

Article in Journal of Environmental Science Computer Science and Engineering & Technology · March 2020
DOI: 10.24214/jecet.B.9.2.19603.

CITATIONS READS
3 3,581

2 authors, including:

Ledisi G. Kabari
Ken Saro-Wiwa Polytechnic, Bori
94 PUBLICATIONS 315 CITATIONS

SEE PROFILE

All content following this page was uploaded by Ledisi G. Kabari on 28 April 2020.

The user has requested enhancement of the downloaded file.

JECETJECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. . E-ISSN: 2278–179X
[DOI: 10.24214/jecet.B.9.2. 19603.

Journal of Environmental Science, Computer Science and

Engineering & Technology
An International Peer Review E-3 Journal of Sciences and Technology

Available online at www.jecet.org

Section B: Computer Science
Research Article

Digital Signal Processing for Predicting Stock Prices in

Financial market
Douglas, T. Minafa and Kabari, L. Giok

Post Graduate unit (Ph.D), Department of Computer Science, Faculty of Natural and Applied Sciences,
Ignatius Ajuru University of Education, Port Harcourt, Rivers State, Nigeria.

Received: 27 March 2020; Revised: 09 April 2020; Accepted: 18 April 2020

Abstract: Financial market is quite dynamic and challenging in trading where investor
will either make money or lose their entire life savings. Predictive logic and analysis tries
to evaluate whether there is any similarity between the historical data and future
tendency. Accurate prediction and analysis of huge amount of financial data facilitate the
retrieval of significant information from large data, which is unknown. In this paper, an
attempt is made for prediction of stock prices and transaction trend to understand its
volatile nature and predict its behavior to gain profits.
Keywords: Stock, Prediction, Prices, Financial Market, Signal, Investment, Trading

1. INTRODUCTION

Tendency to retrieve large amount of financial data from web repository has reshaped the processes of
trading, investment tactic, and risk management; thereby yielding an explosive growth in the research
direction concerning signal processing and financial trading. The stock price prediction is very important
as used by most of the commercial stakeholders as well as common traders [1]. Designing perfect model is
difficult as variation in price is subjected to several factors such as news, multimedia data, and localized

196 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
Digital Signal … Douglas et al.

production, government policy, and previous price and knowledge economy. Prediction model which
considers only one factor may not be ideal because stock indices have always been enticing and quite
intriguing [2] . Predicting the stock flow using techniques and various methods could help investors to act
with greater certainty, and taking the risks, and volatility of an investment into consideration for cheapest
price and/or to highest price in vice versa.
Upward and downward of stock market prices depends on various elements such as amount of demand,
exchange rate, and price of or oil, political and economic trend [3]. Stock market price dispersion can be
considered as time series and without notation to the mentioned factors, and just by finding the sequence
rules of price train, make the price prediction in the future [4]. Predictive tools can be applied on the
historical stock data to determine future when information comes in financial market [5] .
Therefore, beneficial investment in stock market is not that easy, due to likely vulnerability and highly
unpredictable nature of the stock and trading, in terms of values which could possibly improve and fall in
value quickly. Instability is a factual proportion of the variability of profits for a given market survey, the
higher the unpredictability, the more hazardous the stock input. Recorded instability simply known as
unpredictability is the instability of genuine costs of basic stocks. Hence, the aim is to provide predictive
analysis of stock prices in financial market by (i) collecting historical data for stock market information
from trading domain. (ii) Fetch-in the dataset with predictive method and graphical plot using standard
software tool.

2. RELATED WORKS

Previous researches targeted at predicting the price levels of the stock market indices, suggested that
trading strategies guided by forecasts on the direction of price change may be more effective and lead to
higher profits [6] . Many research scholars are now exploring stock market trend prediction using social
media analytics; multiple methods are there to detect the polarity of each tweet/news [7]. Initially mood of
a user on the specific company is considered to analyze the stock price with web analytics, because
polarity of each item in news/tweet has been found to get sentiment through dictionary approach [8] .
German Adhoc messages also had been used as input and for feature selection, chi square method has
been used and SVM algorithm when 65% accuracy is obtained [9] .
Stock prediction model using logistic regression was implemented considering feature index variables,
whereby daily stock trading prediction with logistic regression out performs other method like ANN
prediction model [10] .
Series of stock evaluation on the operation of the financial market like subordinates, for instance, fates
and alternatives have taken a lot of considerations in the recent time. Anticipating these subordinates is
not significant for the hazard purpose [11].
Several persuasive variables on the monetary trading, including political occasions, financial conditions,
exist in spite of the multilateral nature and floats in market costs, market conduct is not totally arbitrary.
Rather, it is represented by a kind of nonlinear dynamical framework. Predicting the subsequent costs is
wholly dependent on the specialized inquiry, which concentrates the market's projection utilizing past
costs and market data [12].
197 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
Digital Signal … Douglas et al.

3. METHODOLOGY

Having sourced for historical trading data in financial match, by fetching and preprocessing, in order to
transform high-frequency data to a ratio matrix and then the outlier technique finds the anomalies in it.
The evaluations on real stock data showed the effectiveness in its prediction. The most significant step for
predicting the behavior of the stock market is data collection; hence the quarterly stock prices and market
capitalization were obtained and used as shown in Table 1.

Table 1: Financial Market and Stock Dataset

Stock Symbol Stock Price Price/Earnings Earnings/Share Market Cap

MMM 222.89 24.31 7.92 1.38721
AOS 60.24 27.76 1.7 1.78348
ABT 56.27 22.51 0.26 1.02121
ABBV 108.48 19.41 3.29 1.81386
CAN 150.51 25.47 5.44 9.87658
ATVI 65.83 31.8 1.28 5.25186
AYI 145.41 18.22 7.43 6.24237
ADBE 185.16 52.31 3.39 9.45502
AAP 109.63 19.54 6.19 8.12361
AMD 11.22 187 0.03 1.11916
AES 10.06 9.96 -1.72 6.92085
AET 178 18.11 5.75 5.91970
AMG 179.11 12.24 12.07 1.04421
Source: Data hub for Financial Market and Nigeria Stock Exchange (NSE)

4. RESULTS AND DISCUSSION

Sequential transformation and distribution plots were presented for the quarterly analysis from time series
model. The trademark with increased earning is quite ideal for prospective investor. Based on seasonal
deviation and expected capitalization for quarterly and year wise returns on stocks, consistent stocks and
promising companies can be figured out as shown thus;

198 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
Digital Signal … Douglas et al.

Fig. 1: API Fetch for Dataset in SPSS

Fig. 2: Initializing the Time Series Models

199 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
Digital Signal … Douglas et al.

Fig. 3: Modeler Selection and Estimation period

Fig. 4: Time Series Function in SPSS

200 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
Digital Signal … Douglas et al.

Fig. 5: Estimated Distribution and Market Series

Fig. 6: Transformation Plot and Expected Flow

201 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
Digital Signal … Douglas et al.

5. CONCLUSION

To earn profit by investing in the stock market with economic viability, intensive planning is germane due
to various uncertainties and its volatile nature. A better way to analyze the trends of stock market for a
rewarding investment is to consider the historical volatility of stocks.

REFERENCES

1. A.Nayak, M.M. Pai and R.M.Pai,. Prediction Models for Indian Stock Market. Procedia in
Computer Science, 2016, 441-449.
2. Y. Feng and D.P. Palomar, a Signal Processing Perspective on Financial Engineering. Glasgow
University Book of Reading,2015, 9(2), -23
3. P. Modi, S. Shah and H. Shah, Big data Analysis in Stock Market Prediction. International
Journal of Engineering Research and Technology, 2019, 8(10), 384-387.
4. D. Shashanklyer, N.R. Kamdar and S. Bahair, Stock Market Prediction using Digital Signal
Processing Models. International Journal of Computer Applications.,2015, 9(6), 47-54
5. C.D.Tilakaratre, S.A. Morris, M.A. Mamador, C.P. Hurst, Predicting Stock Market Index Trading
Signals using Neural Networks ,2014 . Retrieved from http://www.researchgate.com
6. Z.Peng, Stocks Analysis and Prediction Using Big Data Analytics, in 2019 International
Conference on Intelligent Transportation, Data & Smart City (ICITBS), Changsha, China, 2019,
309–312.
7. G.V.Attigeri, P.M. Manohara, R.M. Pai and A. Nayak, Stock market prediction: A big data
approach, in TENCON 2015, IEEE Region 10 Conference, Macao, 1–5.
8. W.Y.Huang, A.P. Chen, Y.H. Hsu, H.Y. Chang and M.W.Tsai, Applying Market Profile Theory
to Analyze Financial Big Data and Discover Financial Market Trading Behavior - A Case Study
of Taiwan Futures Market, 7th International Conference on Cloud Computing and Big Data
(CCBD), Macau, China, 2016,166–169.
9. S.Jeon, B. Hong, J. Kim and H. Lee, Stock Price Prediction based on Stock Big Data and Pattern
Graph Analysis:, in Proceedings of the International Conference on Internet of Things and Big
Data, Rome, Italy,2016, 223–231.
10. P. Singh and A. Thakral, Stock market: Statistical analysis of its indexes and its constituents, in
2017 International Conference on Smart Technologies for Smart Nation (SmartTechCon),
Bangalore, 2017,962–966.
11. S.Tiwari, A. Bharadwaj and S. Gupta, “Stock price prediction using data analytics,” in 2017
International Conference on Advances in Computing, Communication and Control
(ICAC3),2017, Mumbai, 1–5.

202 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.
 Digital Signal … Douglas et al.

12. L. Zhao and L. Wang, Price Trend Prediction of Stock Market Using Outlier Data Mining
Algorithm, in 2015 IEEE Fifth International Conference on Big Data and Cloud Computing,
Dalian, China,2015, 93–98.

* Corresponding Author: Douglas, T. Minafa ,

Post Graduate unit (Ph.D), Department of Computer Science, Faculty of Natural
and Applied Sciences, Ignatius Ajuru University of Education, Port Harcourt,
Rivers State, Nigeria.
Date of publication on line 18.04.2020

203 JECET; JECET; March 2020- May 2020; Sec. B; Vol.9. No.2, 196-203. .
DOI: 10.24214/jecet.B.9.2.19603.

View publication stats