Ruppa Thulasiram

2023-2025 Distinguished Visitor
Share this on:

Dr. Ruppa K. Thulasiram (Tulsi) is a Professor with the Dept. of Computer Science,  Univ. of Manitoba, Canada. He received his PhD (Aerospace Engineering), from Indian Institute of Science and spent years at Concordia Univ., Canada (Mechanical engg.); Georgia Institute of Technology, Atlanta, USA (Aerospace Engg.); and  Univ. of Delaware (Electrical and Computer Engg.) as Post-doc, Research Staff and Research Faculty respectively before taking up a position at Univ. of Manitoba (UM) (Computer Science) in 2000.  His current research interests include Computational Finance (CF), Data Science for Financial Applications (such as Option Pricing, Risk forecasting and etc.), Blockchain Technology for Financial Applications (DeFi – such as Cryptocurrency, Smart Contracts in Collateral Contract Services, etc.), Computational Intelligence (Bio and Nature-inspired Computing) in Finance, Cloud Computing (CC), and related areas.  With his initial training in Mathematics, Physics and Applied Science, he has written many papers in the areas of High Temperature Physics, Applied Math., CF, CC, Computational Intelligence and Blockchain Applications research areas. He has graduated many MSc and PhD students and has received best paper awards in reputed conferences. His research has been funded continuously by the Natural Sciences and Engineering Research Council (NSERC). Canada. Tulsi is currently the chair of the IEEE Computational Intelligence Society’s (CIS) Computational Finance and Economics Technical Committee (CFETC).  He has been an expert reviewer for research funding proposals from Canada, USA and Europe. Tulsi has developed curriculum for CF area and on CC for both graduate and undergraduate level and has been teaching these courses for the past several years.  He has been serving on many administrative committees at UM and outside. Tulsi has organized many conferences and has been editor and guest editor with many journals.

DVP term expires December 2025


Data-Driven Neuro ARCH (DDNA) volatility model for Option Pricing on Cloud Resources   

Due to highly unpredictable nature of financial derivatives market such as options, profiting from these financial products has always been a challenge for investors. One of  the sources of challenge is posed by accurate computation of volatility of the underlying assets (such as stocks) of an option. For this research we use the volatility forecast from Data- Driven Neuro ARCH (DDNA) volatility model along with. the Monte Carlo (MC) simulations to compute option prices. Since the MC method requires a large number of simulations  for better precision, we implement the proposed model on two easily accessible cloud resources (Amazon’s elastic map reduce (EMR) and Google’s Cloud DataProc (GDP) ) using the Hadoop MapReduce paradigm. We show that our model outperforms the existing option  pricing models in terms of efficiency and accuracy. This proposed strategy could be used by investors for computing  option prices precisely with relative ease, allowing them to value the numerous

Comparison of Fuzzy Risk Forecast Intervals for Cryptocurrencies   

Data-driven volatility models and neuro-volatility models have the potential to revolutionize the area of Computational Finance. Volatility measures the variation of a time series data, and thus it is also a driving factor for the risk forecasting of returns from investment in cryptocurrencies. A cryptocurrency is a decentralized medium of exchange that relies on cryptographic primitives to facilitate the trustless transfer of value between different parties. Instead of being physical money, cryptocurrency payments exist purely as digital entries on an online ledger called blockchain that describe specific transactions. Many commonly used risk forecasting models do not take into account the uncertainty associated with the volatility of an underlying asset to obtain the risk forecasts. Some tools from the fuzzy set theory can be incorporated into the forecasting models to account for this uncertainty. Interest in the use of hybrid models for fuzzy volatility forecasts is growing. However, a major drawback is that the fuzzy coefficient hybrid models used in fuzzy volatility forecasts are not data-driven. This paper uses fuzzy set theory with data-driven volatility and data-driven neuro-volatility  forecasts to study the fuzzy risk forecasts. The study focuses on long-term volatility forecasts with daily price data while briefly  exploring forecasting models with high-frequency (hourly) data as an avenue for future research. Simple yet effective models  incorporating fuzziness to obtain fuzzy risk volatility forecasts and fuzzy VaR forecasts are presented. The key underlying  idea, unlike the existing risk forecasting, is the use of a hybrid nonlinear adaptive fuzzy model for volatility.

LSTM based Algorithmic Trading model for Bitcoin

Cryptocurrencies have emerged as an alternative financial asset in the last decade, with their market growing exponentially in recent years. The price of cryptocurrencies is highly volatile and is prone to rapid swings within short periods of time. This behavior makes them a high-risk and high-return financial asset. The efficacy of neural networks in forecasting the  high frequency financial time series has become widely accepted in the research community. This work explored the use of Long Short-Term Memory (LSTM), a neural network based non-linear sequence model, to propose a novel algorithmic trading strategy  for cryptocurrencies. The proposed novel high frequency algorithmic  trading strategy built over an LSTM based short-term  price forecasting is used for Bitcoin and Ethereum. This simple, yet effective trading algorithm uses the network’s price forecasts to make buy and short selling decisions for cryptocurrency based on certain set criteria. The proposed trading strategy gives positive returns when backtested on Bitcoin hourly prices taken from yahoo! finance. We also verified the effectiveness of the trading strategy for Ethereum, the second largest cryptocurrency,  based on the positive backtesting returns. As an extension to the study, the proposed strategy is applied on an even higher frequency (minute by minute) Bitcoin price data, and the strategy  gives positive backtesting returns in this extended study. We also provide fuzzy intervals for the algorithmic return of our strategy and compare those with corresponding intervals on a simple buy and hold strategy.


  • Data-Driven Neuro ARCH (DDNA) volatility model for Option Pricing on Cloud Resources   
  • Comparison of Fuzzy Risk Forecast Intervals for Cryptocurrencies   
  • LSTM based Algorithmic Trading model for Bitcoin