Bio

Ajit Desai is a principal data scientist in the research division of the Bank of Canada's Banking and Payments Department. His current work leverages cutting edge techniques such as artificial intelligence, machine learning, and quantum computing to study payments data (including cryptocurrency data) with the primary objective of making Canada’s digital payments infrastructure safe and efficient. Dr. Desai received his Ph.D. from Carleton University in 2018 in Computational Science and Engineering and M.S. from Indian Institute of Technology Madras in 2011 in Aerospace Engineering.

Staff analytical notes

Machine learning for economics research: when, what and how

Staff Analytical Note 2023-16 Ajit Desai
This article reviews selected papers that use machine learning for economics research and policy analysis. Our review highlights when machine learning is used in economics, the commonly preferred models and how those models are used.
Content Type(s): Staff research, Staff analytical notes Research Topic(s): Central bank research, Econometric and statistical methods, Economic models JEL Code(s): A, A1, A10, B, B2, B23, C, C4, C45, C5, C55

See More

Staff working papers

Finding a Needle in a Haystack: A Machine Learning Framework for Anomaly Detection in Payment Systems

Staff Working Paper 2024-15 Ajit Desai, Anneke Kosse, Jacob Sharples
Our layered machine learning framework can enhance real-time transaction monitoring in high-value payment systems, which are a central piece of a country’s financial infrastructure. When tested on data from Canadian payment systems, it demonstrated potential for accurately identifying anomalous transactions. This framework could help improve cyber and operational resilience of payment systems.
Content Type(s): Staff research, Staff working papers Research Topic(s): Digital currencies and fintech, Financial institutions, Financial services, Financial system regulation and policies, Payment clearing and settlement systems JEL Code(s): C, C4, C45, C5, C55, D, D8, D83, E, E4, E42

From LVTS to Lynx: Quantitative Assessment of Payment System Transition

Staff Working Paper 2023-24 Ajit Desai, Zhentong Lu, Hiru Rodrigo, Jacob Sharples, Phoebe Tian, Nellie Zhang
We quantitatively assess the changes in participants’ payment behaviour from modernizing Canada's high-value payments system to Lynx. Our analysis suggests that Lynx's liquidity-saving mechanism encourages liquidity pooling and early payments submission, resulting in improved efficiency for participants but with slightly increased payment delays.
Content Type(s): Staff research, Staff working papers Research Topic(s): Financial institutions, Financial services, Financial system regulation and policies, Payment clearing and settlement systems JEL Code(s): C, C1, C10, E, E4, E42, G, G2, G28

Improving the Efficiency of Payments Systems Using Quantum Computing

Staff Working Paper 2022-53 Christopher McMahon, Donald McGillivray, Ajit Desai, Francisco Rivadeneyra, Jean-Paul Lam, Thomas Lo, Danica Marsden, Vladimir Skavysh
We develop an algorithm and run it on a hybrid quantum annealing solver to find an ordering of payments that reduces the amount of system liquidity necessary without substantially increasing payment delays.
Content Type(s): Staff research, Staff working papers Research Topic(s): Digital currencies and fintech, Financial institutions, Financial services, Financial system regulation and policies, Payment clearing and settlement systems JEL Code(s): C, C6, C61, C63, D, D8, D83, E, E4, E42, E5, E58

Macroeconomic Predictions Using Payments Data and Machine Learning

Staff Working Paper 2022-10 James Chapman, Ajit Desai
We demonstrate the usefulness of payment systems data and machine learning models for macroeconomic predictions and provide a set of econometric tools to overcome associated challenges.
Content Type(s): Staff research, Staff working papers Research Topic(s): Business fluctuations and cycles, Econometric and statistical methods, Payment clearing and settlement systems JEL Code(s): C, C5, C53, C55, E, E3, E37, E4, E42, E5, E52

Estimating Policy Functions in Payments Systems Using Reinforcement Learning

Staff Working Paper 2021-7 Pablo S. Castro, Ajit Desai, Han Du, Rodney J. Garratt, Francisco Rivadeneyra
We demonstrate the ability of reinforcement learning techniques to estimate the best-response functions of banks participating in high-value payments systems—a real-world strategic game of incomplete information.
Content Type(s): Staff research, Staff working papers Research Topic(s): Digital currencies and fintech, Financial institutions, Financial system regulation and policies, Payment clearing and settlement systems JEL Code(s): A, A1, A12, C, C7, D, D8, D83, E, E4, E42, E5, E58

Using Payments Data to Nowcast Macroeconomic Variables During the Onset of COVID-19

Staff Working Paper 2021-2 James Chapman, Ajit Desai
We use retail payment data in conjunction with machine learning techniques to predict the effects of COVID-19 on the Canadian economy in near-real time. Our model yields a significant increase in macroeconomic prediction accuracy over a linear benchmark model.
Content Type(s): Staff research, Staff working papers Research Topic(s): Econometric and statistical methods, Payment clearing and settlement systems JEL Code(s): C, C5, C53, C55, E, E3, E37, E4, E42, E5, E52

See More

Journal publications

Refereed journals

  • Castro, P. S., Desai, A., Du, H., Garratt, R., & Rivadeneyra, F. (2024). Estimating policy functions in payment systems using reinforcement learning. ACM Transactions on Economics and Computation.
  • McMahon, C., McGillivray, D., Desai, A., Rivadeneyra, F., Lam, J., Lo, T., Marsden, D. and Skavysh, V. (2024). Improving the efficiency of payments systems using quantum computing. Management Science.
  • Chapman, J. T., & Desai, A. (2023). Macroeconomic predictions using payments data and machine learning. Forecasting, 5(4), 652-683.
  • Desai, A., Lu, Z., Rodrigo, H., Sharples, J., Tian, P., & Zhang, N. (2023). From LVTS to Lynx: Quantitative assessment of payment system transition in Canada. Journal of Payments Strategy & Systems, 17(3), 291-314.
  • Chapman, J. T., & Desai, A. (2020). Using payments data to nowcast macroeconomic variables during the onset of COVID-19. Journal of Financial Market Infrastructures, 9(1).
  • Desai, A., Khalil, M., Pettit, C. L., Poirel, D., & Sarkar, A. (2020). Domain Decomposition of Stochastic PDEs: Development of Probabilistic Wirebasket-based Two-level Preconditioners. Journal of Computational Physics (review).
  • Desai, A., Khalil, M., Pettit, C., Poirel, D., & Sarkar, A. (2018). Scalable domain decomposition solvers for stochastic PDEs in high performance computing. Computer Methods in Applied Mechanics and Engineering, 335, 194-222.
  • Desai, A., Witteveen, J. A., & Sarkar, S. (2013). Uncertainty quantification of a nonlinear aeroelastic system using polynomial chaos expansion with constant phase interpolation. Journal of Vibration and Acoustics, 135(5).
  • Desai, A., & Sarkar, S. (2010). Analysis of a nonlinear aeroelastic system with parametric uncertainties using polynomial chaos expansion. Mathematical Problems in Engineering.