See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/343602627 Implementation of Hidden Markov Model For Profit, Loss and Return rate Prediction Research Proposal · August 2020 DOI: 10.13140/RG.2.2.16683.46886 CITATIONS READS 0 118 1 author: Ateeq Ur Rehman University of Engineering and Technology, Peshawar 12 PUBLICATIONS 88 CITATIONS SEE PROFILE All content following this page was uploaded by Ateeq Ur Rehman on 12 August 2020. The user has requested enhancement of the downloaded file. Implementation of Hidden Markov Model For Profit, Loss and Return rate Prediction UNIVERSITY OF ENGINEERING AND TECHNOLOGY PESHAWAR, PAKISTAN POSTGRADUATE RESEARCH PROPOSAL Implementation of Hidden Markov Model For Profit, Loss PROJECT TITLE and Return rate Prediction Computer System Engineering DEPARTMENT AND SPECIALIZTAION STUDENT NAME Ateeq ur rehman FATHER’S NAME Saeed akhtar CONTACT NO. 03159539026 EMAIL ateequrrehman941@gmail.com Registration No 12PWCSE0976 Date of Regn. 07-09-2017 RESEARCH SUPERVISOR CO-SUPERVISOR (IF ANY) COURSES STUDIED S. NO. COURSE NO. AND TITLE GRADE 1. Advance Artificial Intelligence A- 2. Wireless Networks B 3. Advanced Software Engineering B+ 4. Network Modelling 5. 6. 7. 8. 9. CGPA 3.35 Implementation of Hidden Markov Model For Profit, Loss and Return rate Prediction 1. INTRODUCTION The stock exchange is a network that provides a platform for pretty much all major economic transactions within the world at a dynamic rate known as the stock worth that relies on market equilibrium. Predicting this stock worth offers huge profit opportunities that area unit a large motivation for analysis during this space. Information of a stock worth beforehand by even a fraction of a second may result in high profits. Similarly, a probabilistically correct prediction will be very profitable. A hidden Markov model (abbreviated HMM) is, loosely speaking, a Markov chain observed in noise. Indeed, the model comprises a Markov chain, which we will denote by {Xk}k≥0, where k is an integer index. This Markov chain is often assumed to take values in a finite set, but we will not make this restriction in general, thus allowing for a quite arbitrary state space. Now, the Markov chain is hidden, that is, states are not observable. Recall In a regular Markov model, the state is directly visible to the observer, and therefore the state transition probabilities are the only parameters. In a hidden Markov model, the state is not directly visible, but output, dependent on the state, is visible. Each state has a probability distribution over the possible output tokens. Therefore the sequence of tokens generated by an HMM gives some information about the sequence of states. Note that the adjective 'hidden' refers to the state sequence through which the model passes, not to the parameters of the model; even if the model parameters are known exactly, the model is still 'hidden'. 1.1 The research problem HMM are extensively used for pattern recognition and classification issues due to its welltried quality for modelling dynamic systems. However, victimisation HMM for predicting future events isn't easy. Here we tend to use only 1 HMM that's trained on the dataset of the chosen window. The trained HMM is employed to look for the variable of interest activity information pattern from the dataset. By interpolating the close values of those datasets forecasts measure ready. The results obtained victimisation HMM square measure encouraging and HMM offers a brand new paradigm for securities market prediction, a part that has been of abundant analysis interest recently PREC Member PREC Member PREC member Implementation of Hidden Markov Model For Profit, Loss and Return rate Prediction 2. LITERATURE REVIEW AND CONCEPTUAL FRAMEWORK In Recent years, a variety of forecasting methods have been proposed and implemented for the stock market analysis. A brief study on the literature survey is presented. Markov Process is a stochastic process where the probability at one time is only conditioned on a finite history, being in a certain state at a certain time. Markov chain is “Given the present, the future is independent of the past”. HMM is a form of probabilistic finite state system where the actual states are not directly observable, to get an idea about the trend analysis of stock market behaviour using Hidden Markov Model (HMM). The estimate once followed over a particular period will sure repeat in future. his paper presents Hidden Markov Models (HMM) approach for forecasting stock price for interrelated markets. We apply HMM to forecast some of the airlines stock. 3. APPROACH AND METHODOLOGY The main purpose of this part is to introduce the methodology we use in this project. In order to apply the Hidden Markov Chain, we divide the total historical data of 1400 data points into two parts. The first part consisted of the first 1000 numbers and is used to construct a well enough model while the second part of the rest 400 numbers is used to implement our trading strategy to see how well it works. In finance, stock prices are often assumed to follow a Markov process. This means that the present value is all that is needed for predicting the future, and that the past history and the taken path to today’s value is irrelevant. Considering that equity and currency are both financial assets, traded under more or less the same conditions, it would not seem farfetched assuming that currency prices also follow a Markov process. Data Collection: The complete set of data for the proposed study has been taken from yahoofinance.com. The 400 days, 1000 values of the stock market trading. PREC Member PREC Member PREC member Implementation of Hidden Markov Model For Profit, Loss and Return rate Prediction 4. REFERENCE LIST 1. Md. Rafiul Hassan and Baikunth Nath, “Stock Market forecasting using Hidden Markov Model: A New Approach,” Proceeding of the 2005 5th international conference on intelligent Systems Design and Application 0-7695-2286-06/05, IEEE, 2005. 2. L.R Rabiner, “A tutorial on HMM and Selected Applications in Speech Recognition,” In:[WL], proceedings of the IEEE,Vol. 77 (2), pp. 267-296,199 3. Kavitha G, Udhayakumar A and Nagarajan D, Stock Market Trend Analysis Using Hidden Markov Models, , 2011, 5, 11-18 4. Md. Rafiul Hassan, Baikunth Nath and Michael Kirley, “ A fusion model of HMM, ANN and GA for stock market forecasting,” Expert systems with Applications., pp. 171180,2007. 5. A. S. Weigend A. D. Back, “What Drives Stock Returns?-An IndependentComponent Analysis,” In Proceedings of the IEEE/IAFE/INFORMS 1998 Conference on Computational Intelligence for Financial Engineering, IEEE, New York., pp. 141156,1998. 6 H.White, “Economic prediction using neural networks: the case of IBM daily stock returns,” In Proceedings of the second IEEE annual conference on neural networks., II, pp. 451–458,1988. PREC Member View publication stats PREC Member PREC member