Peter Jacko has co-authored over 40 peer-reviewed publications which have contributed to the methodological areas of stochastic modelling, applied probability, design of experiments, performance evaluation, queueing theory, dynamic programming, optimisation, and reinforcement learning. These areas provide foundation for the modern disciplines of business analytics, data science, and artificial intelligence. The leading themes of his research are stochastic modelling of real problems and devising tractable and well-performing solutions for efficient allocation of scarce resources over time. His main research line recently has been the optimal patient-centric design of modern adaptive clinical trials, which can often be modelled as variants of the multi-armed bandit problem.

I always welcome students with strong quantitative (mathematics, computing, statistics, etc.) background interested in solving problems in the design and management of complex systems. In particular, you will be looking for carrying out research in areas such as operational research, performance evaluation, stochastic modelling, approximate dynamic programming, queueing theory, applied probability, and/or machine learning, motivated by real-world problems in business decision-making, public health proccesses or communications networks. Currently I am specifically looking for students interested in research on the optimal design and conduct of sequential experiments and modern adaptive clinical trials (such as platform, umbrella and basket trials), which can be modelled as multi-armed bandit problems. I have co-supervised around 10 PhD students, some of which have received awards for their research. PhD funding is available through the Department of Management Science and through the STOR-i Doctoral Training Centre. If you are a self-funded PhD applicant (or a master/PhD student elsewhere interested in visiting me for a short period), please contact me directly by e-mail.

Peter Jacko is a Senior Decision Scientist for Berry Consultants, which he joined in 2021, and a Senior Lecturer (Associate Professor) in Management Science at Lancaster University, UK, which he joined in 2013 under the LANCS Initiative and where he is also member of the Data Science Institute and STOR-i Centre for Doctoral Training. Between 2009 and 2018 he was affiliated with the Basque Center for Applied Mathematics, Spain, where he was formerly a postdoctoral fellow, researcher, co-leader, and an external scientific member in the Networks research group, in Data Science research area. Peter earned his Ph.D. in Business Administration and Quantitative Methods (2009) and D.E.A. in Statistics and Operations Research (2006) from the Universidad Carlos III de Madrid, Spain, and received his Mgr. (2003) and Bc. (2002) degrees in Mathematics from the Univerzita P.J. Šafárika v Košiciach, Slovakia.

Peter is devoted to the development of methods for the solution of problems in the design and management of complex systems such as health processes, business decision-making, and communications networks. The leading themes of his research are stochastic modelling of real problems and devising tractable and well-performing solutions for efficient allocation of scarce resources over time. His research work benefits from the interaction of mathematics, statistics, computing, and/or economics, typical for the discipline of operational research, and he also has extensive experience in scientific computer programming, including simulation. His main research line recently has been the optimal patient-centric design of modern adaptive clinical trials, which can often be modelled as variants of the multi-armed bandit problem.

His research interests are in:

• Fields: Mathematics, Computer Science, Economics & Business, Engineering, Business Analytics, Data Science
• Areas: Operational Research, Performance Evaluation, Stochastic Modelling, Queueing Theory, Applied Probability, Machine Learning
• Problems: Resource Allocation, Scheduling, Sequential Learning, Networks Optimisation, Multi-armed Bandits
• Methods: Markov Decision Processes, Dynamic Programming, Stochastic/Bayesian Analysis, Heuristics Design

His research efforts have been motivated by and the results are aimed to apply to:

• Business Decision-Making: Retail Industry, Contact Centres
• Public Health Processes: Adaptive Clinical Trials, Personalised Medicine
• Communications Networks: Wireless Data Networks (D2D, 4G LTE), Internet (TCP, ICN)

Personal webpage: http://www.lancaster.ac.uk/staff/jacko/

Amin Yarahmadi (2023): Stochastic Models For Dynamic Resource Allocation

Livia Stark (2022): Evaluation of the Intelligence Collection and Analysis Process

Ugur Satic (2022): Simulation and Optimization of Scheduling Policies in Dynamic Stochastic Resource-Constrained Multi-Project Environments

Stephen Ford (2021): On The Dynamic Allocation of Assets Subject To Failure And Replenishment

Francis Garuba (2020): Robust and Stochastic Optimisation Approaches to Network Capacity Expansion and QoS Improvement

Faye Williamson (2020): Bayesian Bandit Models for the Design of Clinical Trials