Books by Jaydip Sen
Machine Learning in the Analysis and Forecasting of Financial Time Series
Machine Learning in the Analysis and Forecasting of Financial Time Series, 2022
This book is a collection of real-world cases, illustrating how to handle challenging and volatil... more This book is a collection of real-world cases, illustrating how to handle challenging and volatile financial time series data for a better understanding of their past behavior and robust forecasting of their future movement. It demonstrates how the concepts and techniques of statistical, econometric, machine learning, and deep learning are applied to build robust predictive models, and the ways in which these models can be used for constructing profitable portfolios of investments. All the concepts and methods used here have been implemented using R and Python languages on TensorFlow and Keras frameworks. The book will be particularly useful for advanced postgraduate and doctoral students of finance, economics, econometrics, statistics, data science, computer science, and information technology.
Computer and Network Security, Jun 1, 2020
In the era of Internet of Things and with the explosive worldwide growth of electronic data volum... more In the era of Internet of Things and with the explosive worldwide growth of electronic data volume, and associated need of processing, analysis and storage of such humongous volume of data, several new challenges are faced in protecting privacy of sensitive data and securing systems by designing novel schemes for secure authentication, integrity protection, encryption and non-repudiation. Lightweight symmetric key cryptography and adaptive network security algorithms are in demand for mitigating these challenges. This book presents some of the state-of-the-art research work in the field of cryptography and security in computing and communications. It is a valuable source of knowledge for researchers, engineers, practitioners, graduate and doctoral students who are working in the field of cryptography, network security and security and privacy issues in the Internet of Things (IoT), and machine learning application in security. It will also be useful for faculty members of graduate schools and universities
Analysis and Forecasting of Financial Time Series Using R : Models and Applications , Aug 9, 2017
Analysis and prediction of stock market time series data have attracted considerable interest fro... more Analysis and prediction of stock market time series data have attracted considerable interest from the research community over the last decade. Rapid development and evolution of sophisticated algorithms for statistical analysis of time series data and availability of high-performance hardware have made it possible to process and analyze high volume stock market time series data effectively, in real-time. Among many other important characteristics and behavior of such data, forecasting is an area which has witnessed considerable focus. This book presents some of the state of the art research work in the field of time series analysis and forecasting. Rich libraries of R software have been used for time series decomposition and for designing of efficient forecasting approaches. It will surely be a valuable source of knowledge for researchers, engineers, practitioners, analysts, data scientists and graduate and doctoral students who are working in the field of econometrics, statistical modeling, time series analysis, forecasting and financial analytics. It will also be useful for faculty members of graduate schools and universities.
Advances in Security in Computing and Communications, Jul 13, 2017
In the era of Internet of Things (IoT) and with the explosive worldwide growth of electronic data... more In the era of Internet of Things (IoT) and with the explosive worldwide growth of electronic data volume, and associated need of processing, analysis, and storage of such humongous volume of data, several new challenges are faced in protecting privacy of sensitive data and securing systems by designing novel schemes for secure authentication, integrity protection, encryption, and non-repudiation. Lightweight symmetric key cryptography and adaptive network security algorithms are in demand for mitigating these challenges. This book presents some of the state-of-the-art research work in the field of cryptography and security in computing and communications. It is a valuable source of knowledge for researchers, engineers, practitioners, graduates, and doctoral students who are working in the field of cryptography, network security, and security and privacy issues in the Internet of Things (IoT). It will also be useful for faculty members of graduate schools and universities.
In the era of Internet of Things and with the explosive worldwide growth of electronic data volum... more In the era of Internet of Things and with the explosive worldwide growth of electronic data volume, and associated need of processing, analysis, and storage of such humongous volume of data, it has now become mandatory to exploit the power of massively parallel architecture for fast computation. Cloud computing provides a cheap source of such computing framework for large volume of data for real-time applications. It is, therefore, not surprising to see that cloud computing has become a buzzword in the computing fraternity over the last decade. This book presents some critical applications in cloud frameworks along with some innovation design of algorithms and architecture for deployment in cloud environment. It is a valuable source of knowledge for researchers, engineers, practitioners, and graduate and doctoral students working in the field of cloud computing. It will also be useful for faculty members of graduate schools and universities.
SECURITY ISSUES IN A NETWORKED AGE - RESEARCH COLLECTION, Jul 1, 2016
Wireless networks are truly pervasive in the modern environment: from the workplace and the home,... more Wireless networks are truly pervasive in the modern environment: from the workplace and the home, to implanted medical devices. Network security, therefore, is of paramount importance. This volume begins with an overview of the security vulnerabilities of wireless sensor networks, but also offers some means of defence against them. It goes on to propose ways of securing routing in wireless mesh networks. Two further chapters offer in-depth studies of secure and privacy-preserving data protocols for wireless sensor and mesh networks. The book concludes with an overview of the history of homomorphism encryption as a means of securing data, also covering some emerging trends in which this form of encryption offers exciting new possibilities.
In an age of explosive worldwide growth of electronic data storage and communications, effective ... more In an age of explosive worldwide growth of electronic data storage and communications, effective protection of information has become a critical requirement. When used in coordination with other tools for ensuring information security, cryptography in all of its applications, including data confidentiality, data integrity, and user authentication, is a most powerful tool for protecting information. This book presents a collection of research work in the field of cryptography. It discusses some of the critical challenges that are being faced by the current computing world and also describes some mechanisms to defend against these challenges. It is a valuable source of knowledge for researchers, engineers, graduate and doctoral students working in the field of cryptography. It will also be useful for faculty members of graduate schools and universities.
Cryptography will continue to play important roles in developing of new security solutions which ... more Cryptography will continue to play important roles in developing of new security solutions which will be in great demand with the advent of high-speed next-generation communication systems and networks. This book discusses some of the critical security challenges faced by today's computing world and provides insights to possible mechanisms to defend against these attacks. The book contains sixteen chapters which deal with security and privacy issues in computing and communication networks, quantum cryptography and the evolutionary concepts of cryptography and their applications like chaos-based cryptography and DNA cryptography. It will be useful for researchers, engineers, graduate and doctoral students working in cryptography and security related areas. It will also be useful for faculty members of graduate schools and universities.
The purpose of this book is to present some of the critical security challenges in today's comput... more The purpose of this book is to present some of the critical security challenges in today's computing world and to discuss mechanisms for defending against those attacks by using classical and modern approaches of cryptography and other defence mechanisms. It contains eleven chapters which are divided into two parts. The chapters in Part 1 of the book mostly deal with theoretical and fundamental aspects of cryptography. The chapters in Part 2, on the other hand, discuss various applications of cryptographic protocols and techniques in designing computing and network security solutions. The book is expected to be useful for researchers, engineers, graduate and doctoral students working in cryptography and security related areas.
Book Chapters by Jaydip Sen
Analysis and Forecasting of Financial Time Series: Selected Cases, 2022
This chapter presents a step-by-step approach to designing mean-variance optimization-based portf... more This chapter presents a step-by-step approach to designing mean-variance optimization-based portfolios of stocks chosen from six important sectors listed on the National Stock Exchange (NSE) of India. Based on the NSE’s report on December 31, 2020, the top ten stocks of each sector are first identified (NSE Website). Three portfolios are built for each sector maximizing the Sharpe ratio, the Sortino ratio, and the Calmar ratio based on the historical stock prices from January 1, 2017, to December 31, 2020. The portfolios are tested over the period from January 1, 2021, to December 31, 2021, based on their cumulative returns. For each sector, the portfolio that yields the highest cumulative returns for the training and the test periods is identified. The ratio for which the portfolios yield the highest cumulative returns for the majority of the sectors for the training and the test periods is identified. For the mean-variance portfolio design approach, the ratio yielding the maximum cumulative return for the majority of the sectors is the one that should be maximized for designing the portfolios for the sectors. Moreover, the sectors for which the same portfolio has yielded the highest cumulative returns for both the training and the test periods are also identified. For these sectors, the investors will be able to maximize their profit using the same approach to the portfolio design.
Analysis and Forecasting of Financial Time Series: Selected Cases, 2022
This chapter proposes a portfolio design method using mean-variance optimization on stocks chosen... more This chapter proposes a portfolio design method using mean-variance optimization on stocks chosen from twelve sectors listed on the National Stock Exchange (NSE) of India. The top ten stocks of each sector are identified in the NSE’s report published on December 31, 2020 (NSE Website). For each sector, three portfolios are designed to maximize the Sharpe ratio, the Sortino ratio, and the Calmar ratio, on stock prices from January 1, 2017, to December 31, 2020. The portfolios are tested over the period from January 1, 2021, to December 31, 2021, based on their cumulative returns. For each sector, the portfolio that yields the highest cumulative return over the training and the test periods is identified. The ratio for which the portfolios yield the highest cumulative returns for the majority of the sectors is identified. For designing mean-variance portfolios for the twelve sectors, the ratio yielding the highest cumulative return for the majority of the sectors is the one that should be used for maximization. Moreover, the sectors for which the same portfolio has yielded the highest cumulative returns for both the training and the test periods are also identified. For these sectors, the investors will be able to maximize their profit using the same approach to the portfolio design.
Analysis and Forecasting of Financial Time Series: Selected Cases, 2022
This chapter presents an algorithmic approach for building efficient portfolios by selecting stoc... more This chapter presents an algorithmic approach for building efficient portfolios by selecting stocks from fourteen sectors listed on the National Stock Exchange (NSE) of India. Based on the report of the NSE published on December 31, 2020, the top ten stocks with the highest free-float market capitalization from thirteen sectors and the 50 stocks included in the NIFTY 50 are first identified (NSE Website). Portfolios are built using the MVP and the HRP algorithms using the historical prices of the stocks from January 1, 2016, to December 31, 2020. The portfolios are backtested on the training data of the stock prices from January 1, 2016, to December 31, 2020, and on the test data from January 1, 2021, to December 31, 2021. The portfolios are evaluated based on their cumulative returns and Sharpe ratios over the training and test periods.
Analysis and Forecasting of Financial Time Series: Selected Cases, 2022
This chapter presents a gamut of volatility models based on the approach of generalized autoregre... more This chapter presents a gamut of volatility models based on the approach of generalized autoregressive conditional heteroscedasticity (GARCH) (Bauwens et al., 2006; Bollerslev, 1986; Curto et al., 2007; Hung, 2009; Lin, 2018). Several models are built using the historical stock price data in the NSE from January 1, 2010, to April 30, 2021. For each of the six important sectors, the ten most critical stocks are selected for the analysis. The six sectors are as follows: auto, banking, consumer durable, information technology (IT), pharma, and fast-moving consumer goods (FMCG). Several GARCH models are built, fine-tuned, and then backtested on the out-of-sample data. Extensive analysis is done on the evaluation of the performance of the volatility models.
Analysis and Forecasting of Financial Time Series: Selected Cases, 2022
The current work proposes a deep learning LSTM model for accurately predicting future stock price... more The current work proposes a deep learning LSTM model for accurately predicting future stock prices. The model automatically extracts the historical prices of the stocks using a Python function that uses the ticker names of the stocks in the NSE for an interval specified by a start date and an end date. Using the historical prices of 70 stocks from fourteen sectors, the model is used to predict future stock prices. Based on the prediction of the model, buy/sell decisions are taken for each stock and finally, the total profit earned for each stock is computed. Based on the aggregate profit of all the stocks for a given sector, the overall profitability of a sector is derived. A comparative analysis of the profitability of the fourteen sectors and the prediction accuracy of the LSTM model is evaluated.
Analysis and Forecasting of Financial Time Series: Selected Cases, 2022
In this chapter, our goal is to study the behavioral pattern exhibited by the time series of the ... more In this chapter, our goal is to study the behavioral pattern exhibited by the time series of the mid-cap sector of India so that the salient properties of that sector can be better understood. By its definition, a mid-cap company has a market capitalization between Indian Rupees (INR) 50 billion to INR 200 billion. For our study, the monthly average index values of the mid-cap sector are used for the period January 2010 - December 2021 as per the Bombay Stock Exchange (BSE). The monthly time series data is decomposed into its three components using functions defined in the R programming language. Based on the decomposition results, we demonstrate how several exciting characteristics of the time series can be extracted to gain valuable insights into its behavioral pattern. We particularly illustrate how a more in-depth analysis of the trend, seasonal and random components provides us with helpful information about the growth pattern, seasonal properties, and randomness exhibited by the time series index values. For predicting future behavioral patterns, we also propose an extensive framework for time series forecasting consisting of six methods of prediction of time series index values. The six forecasting methods are critically analyzed in terms of forecasting accuracy.
"Analysis and Forecasting of Financial Time Series Using Statistical, Econometric, Machine Learning and Deep Learning Models, edited by Jaydip Sen and Sidra Mehtab to be published by Cambridge Scholars Publishing Limited, UK. , 2020
In this chapter, we propose several machine learning and deep learning-based predictive models fo... more In this chapter, we propose several machine learning and deep learning-based predictive models for predicting NIFTY 50 stock price movement in NSE of India. We use daily stock price values for the period January 4, 2010 to December 31, 2018, as the training dataset for building the models, and apply the models to predict the daily stock price movement and actual closing value of the stock for the period January 1, 2019, to December 31, 2019. The predictive model is further augmented by incorporating a sentiment analysis module that analyses public sentiments in Twitter on NIFTY 50 stocks. The output of the sentiment analysis module is used as the second input to the model in addition to the historical NIFTY 50 data to predict future stock price movement. Following the approach proposed by Mittal and Goel, we have classified the public sentiment in Twitter into four classes and studied the causal effect of those sentiment classes on NIFTY 50 stock price movement using the Granger Causality Test (Mittal & Goel, 2012).
"Analysis and Forecasting of Financial Time Series Using Statistical, Econometric, Machine Learning and Deep Learning Models", edited by Jaydip Sen and Sidra Mehtab to be published by Cambridge Scholars Publishing Limited
In this chapter, we propose a granular approach to stock price prediction by combining statistica... more In this chapter, we propose a granular approach to stock price prediction by combining statistical and machine learning methods of prediction on technical analysis of stock prices. We present several approaches for short-term stock price movement forecasting using various classification and regression techniques and compare their performance in the prediction of stock price movement. We believe this approach will provide several useful information to the investors in the stock market who are particularly interested in short-term investments for profit. This work is an extended version of our previous work (Sen & Datta Chaudhuri, 2017c). In the present work, we have extended our predictive framework by including five more classification and five more regression models including an advanced deep learning model.
The rest of the chapter is organized as follows. In the section titled “Problem Statement”, we present a clear statement of our problem at hand. The section titled “Related Work”, provides a brief review of the literature on stock price movement modeling and prediction. In the section titled “Methodology”, we present a detailed discussion on the methodology that we have followed in this work. The section titled “Performance Results” describes the details of all the predictive models built in this work and the results they have produced. A comparative analysis has been presented on the performance of the models in this section. Finally, the section titled “Conclusion” concludes the chapter.
COMPUTER AND NETWORK SECURITY, Mar 20, 2020
Machine learning and data mining algorithms play important roles in designing intrusion detection... more Machine learning and data mining algorithms play important roles in designing intrusion detection systems. Based on their approaches towards the detection of attacks in a network, intrusion detection systems can be broadly categorized into two types. In the misuse detection systems, an attack in a system is detected whenever the sequence of activities in the network match with a known attack signature. In the anomaly detection approach, on the other hand, anomalous states in a system are identified based on a significant difference in the state transitions of the system from its normal states. This chapter presents a comprehensive discussion on some of the existing schemes of intrusion detection based on misuse detection, anomaly detection and hybrid detection approaches. Some future directions of research in the design of algorithms for intrusion detection are also identified.
Analysis and Forecasting of Financial Time Series Using R: Models and Applications, 2017
Analysis and prediction of stock market time series data has attracted considerable interest from... more Analysis and prediction of stock market time series data has attracted considerable interest from the research community over the last decade. Rapid development and evolution of sophisticated algorithms for statistical analysis of time series data, and availability of high-performance hardware has made it possible to process and analyze high volume stock market time series data effectively, in real-time. Prediction of stock prices using econometrics and machine learning based approaches poses significant challenges to the research community since the movement of stock prices are essentially random in its nature. With the rapid development and evolution of algorithms using sophisticated machine learning and artificial intelligence concepts, of late, it has become possible to handle large volume of complex time series data for statistical analysis in real time using high-performance hardware and parallel computing architecture. Accordingly, robust predictive models are being built for achieving more accuracy in forecasting of highly random and stochastic stock price movements. This chapter presents a highly reliable and accurate forecasting framework for predicting the time series index values of the metal sector in India. First, a time series decomposition approach is followed to understand the behavior of the metal sector time series for the period January 2010 till December 2016. Based on the structural analysis of the time series, six methods of forecasting are designed. These methods are applied to predict the time series index values for the months of 2016. Extensive results are presented to demonstrate the effectiveness of the proposed decomposition approaches of time series and the efficiency of the six forecasting methods.
Analysis and Forecasting of Financial Time Series Using R: Models and Applications, 2017
Prediction of stock prices using time series analysis is quite a difficult and challenging task s... more Prediction of stock prices using time series analysis is quite a difficult and challenging task since the stock prices usually depict random patterns of movement. However, the last decade has witnessed rapid development and evolution of sophisticated algorithms for complex statistical analysis. These algorithms are capable of processing a large volume of time series data executing on high-performance hardware and parallel computing architecture. Thus computations which were seemingly impossible to perform a few years back are quite amenable to real-time time processing and effective analysis today. Stock market time series data are large in volume, and quite often need real-time processing and analysis. Thus it is quite natural that research community has focused on designing and developing robust predictive models for accurately forecasting stochastic nature of stock price movements. This work presents a time series decomposition-based approach for understanding the past behavior of the realty sector of India, and forecasting its behavior in future. While the forecasting models are built using the time series data of the realty sector for the period January 2010 till December 2015, the prediction is made for the time series index values for the months of the year 2016. A detailed comparative analysis of the methods are presented with respect to their forecasting accuracy and extensive results are provided to demonstrate the effectiveness of the six proposed forecasting models.
Uploads
Books by Jaydip Sen
Book Chapters by Jaydip Sen
The rest of the chapter is organized as follows. In the section titled “Problem Statement”, we present a clear statement of our problem at hand. The section titled “Related Work”, provides a brief review of the literature on stock price movement modeling and prediction. In the section titled “Methodology”, we present a detailed discussion on the methodology that we have followed in this work. The section titled “Performance Results” describes the details of all the predictive models built in this work and the results they have produced. A comparative analysis has been presented on the performance of the models in this section. Finally, the section titled “Conclusion” concludes the chapter.