Your browser is unsupported

We recommend using the latest version of IE11, Edge, Chrome, Firefox or Safari.

Photo of Pakiman, Parshan

Parshan Pakiman

Doctoral Student in Business Administration: Information and Decision Sciences Emphasis

Department of Information and Decision Sciences

Pronouns: He/Him/His

Contact

Building & Room:

UH 2432

Address:

601 S. Morgan St.

CV Link:

Parshan Pakiman

About

Welcome to my UIC homepage! My name is Parshan Pakiman, and I am a Ph.D. candidate in Information and Decision Sciences (IDS) at the University of Illinois at Chicago (UIC). Before joining UIC, I received my Bachelor of Science in Applied Mathematics from the School of Mathematics, Statistics, and Computer Science at the University of Tehran. I have the pleasure of being advised by professors Selva Nadarajah and Negar Soheili. My main research interests include:

(i) Working towards off-the-shelf RL algorithms that sidestep hyperparameter tunings and heuristic hand-engineerings, making RL accessible to users without domain knowledge.

(ii) Learning stochastic models from data trajectories that manage risks associated with model misspecification and/or poorly tuned hyperparameters.

(iii) Tackling real-world problems in dynamic pricing, marketing, option pricing, inventory control, and e-commerce by implementing methods based on novel machine learning and optimization platforms, i.e., TensorFlow and Gurobi.

Classes Taught (Teaching Assistant)

  • Introduction to Operations Management (UIC, IDS 532)
  • Statistical Models and Methods for Business Analytics (UIC, IDS 575)
  • Business Forecasting (UIC, IDS 476)
  • Business Data Mining (UIC, IDS 472
  • Business Statistics (UIC, IDS 270)
  • Numerical Linear Algebra (UT)
  • Numerical Analysis (UT)

 

Selected Publications

B. Chen, S. Nadarajah, P. Pakiman, S. Jasin. Self-adapting Robustness in Demand Learning. Under first round review at Operations Research.

P. Pakiman, S. Nadarajah, N. Soheili, Q. Lin. Self-guided Approximate Linear Programs. Under second round review at Management Science. A workshop version is accepted at the NeurIPS workshop on Self-Supervised Learning — Theory and Practice.

A. Chenreddy, P. Pakiman, S. Nadarajah, R. Chandrasekaran, R. Abens. SMOILE: A Shopper Marketing Optimization and Inverse Learning Engine. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019. Acceptance rate 6.4%.

“Box-suite Optimization for Online Retailers.” Joint work with Selvaprabu Nadarajah and Yun Fong Lim. (Work in progress).

Publication Aggregators

Service to Community

Reviewer

  • Annals of Operations Research, Fall 2020 - Present
  • Computers & Operations Research, Spring 2019 - Present
  • Electronic Commerce Research, Spring 2018 - Present
  • Information Systems and Operational Research, Fall 2018 - Present

Conference Organization

  • Session Chair, Recent Advances in Reinforcement Learning, INFORMS Annual Meeting Fall 2021
  • Session Co-Chair, Social Responsibility and Risk in Supply Chains, INFORMS Annual Meeting Fall 2021

Notable Honors

2021 - Present, Beta Gamma Sigma (BGS) Membership, College of Business, University of Illinois at Chicago

2017 - Present, Doctoral Scholarship and CBA Doctoral Fellowship, Department of Information and Decision Sciences, University of Illinois at Chicago

2017 - Present, Graduate Assistantship, College of Business, University of Illinois at Chicago

2016, Best Student Award, Department of Mathematics, Statistics and Computer Science, University of Tehran

2016, Graduate Entrance Scholarship, Department of Mathematics, Statistics and Computer Science, University of Tehran, Iran

2016, Technical Qualification, 2D Soccer Simulation League

2010, Technical Qualification, Khwarizmi International Award, Soccer 2D Simulation League

Education

University of Illinois at Chicago (UIC), Chicago, IL Spring 2017 - (Expected) Fall 2021
Ph.D.: Information and Decision Sciences
Thesis title: Mitigating Model Risk in Reinforcement Learning: Self-adapting Methods with Applications in Operations and Marketing
Co-advisors: Professors Selva Nadarajah and Negar Soheili

University of Illinois at Chicago, Chicago, IL Spring 2017 - (Expected) Fall 2021
M.Sc.: Business Analytics (Expected) Fall 2021

University of Tehran, Tehran, Iran Fall 2012 - Fall 2016
B.Sc.: Applied Mathematics

Professional Memberships

Institute for Operations Research and the Management Sciences (INFORMS), Fall 2018 - Present
Production and Operations Management Society (POMS)
IDS committee for organizing curriculum of programming in R, Spring 2021 - Present
Beta Gamma Sigma (BGS) society, Spring 2021 - Present

Selected Presentations

  • Putting Social Responsibility on the Menu: AI-Guided Tool Selection that Aligns Worker and Social Objectives
    • POMS 31st Annual Conference, Virtual, Spring 2021
  • Self-adapting Robustness in Demand Learning
    • INFORMS Annual Meeting, Virtual, Fall 2020
    • INFORMS Revenue Management and Pricing Student Live Paper Series, Link, Virtual, Fall 2020
  • Self-guided Approximate Linear Programs
    • ┬áINFORMS Annual Meeting, Anaheim, CA, Fall 2021
    • POMS 30th Annual Conference, Washington D.C., Spring 2019
    • INFORMS Annual Meeting, Phoenix, AZ, Fall 2018
    • POMS 29th Annual Conference, Houston, TX Spring, 2018
  • SMOILE: A Shopper Marketing Optimization and Inverse Learning Engine
    • ACM SIGKDD, International Conference on Knowledge Discovery & Data Mining, Link, Anchorage, AK, Summer 2019

Research Currently in Progress

P. Pakiman, S. Nadarajah, Y. F. Lim. Guiding Agents via Menus when Optimization and/or Learning Costs are High. In preparation to submit to AAAI 2022.

P. Pakiman, S. Nadarajah, Y. F. Lim. Putting Social Responsibility on the Menu: AI-Guided Tool Selection that Aligns Worker and Social Objectives. In preparation to submit to Manufacturing & Service Operations Management.

D. R. Jiang, S. Nadarajah, P. Pakiman, Y. Wang. Comparing Approximate Dynamic Programming Algorithms on Operations Management Applications. Working paper.