About me

Naman is a Technical Product Owner in the Data Science team at FLYR Labs , where he leads a team of data scientists to build exciting machine learning models that can bring value to existing revenue management systems for airlines. He is responsible for driving the development and implementation of advanced machine learning algorithms and statistical models that leverage contextual information to optimize pricing strategies for airlines.

Prior to this, his research focused on dynamic pricing with contextual information, where he developed machine learning algorithms and statistical methods to analyze revenue management data and engineer computational techniques. His work has been published in esteemed journals such as the Journal for Applied Analytics in Institute for Operations Research and the Management Sciences (INFORMS) and Airline Group of the International Federation of Operational Research Societies (AGIFORS).

Naman's expertise in machine learning solutions has been deployed by major airlines and travel providers in Europe and Asia through his role as a machine learning engineer, research infrastructure manager, and software engineer at Deepair. He developed software tools and frameworks that are used by in-house data science teams and researchers at esteemed institutions such as the University of Illinois at Urbana Champaign, Imperial College London, and the University of Notre Dame. He was a part of the team that achieved New Distribution Capability (NDC) level 4 certification by the International Air Transport Association (IATA).

Naman received his masters of science in Industrial Engineering from the University of Illinois at Urbana Champaign, IL. He is a recipient of Japan student services organization (JASSO) scholarship for innovation program by University of Tokyo, Japan. He was awarded computational biology scholarship for associate researcher at Ritsumeikan University, Japan. He has a bachelor of technology in Chemical Engineering and minor in Entrepreneurship both with academic excellence award from Indian Institute of Technology, Hyderabad, India.


Work Experience

  • FLYR Labs San Francisco, CA
    Technical Product Owner [Aug 2022 - Current]
  • Deepair Solutions London, UK
    Data Scientist [May 2018 - July 2022]

Education

  • University of Illinois Urbana-Champaign, IL
    Master of Science in Advanced Analytics.
    Thesis: Dynamic Pricing for Airline Ancillaries with Customer Context.
  • Indian Institute of Technology Hyderabad, India
    Bachelor of Technology in Chemcial Engineering with entrepreneurship minor.

Publications

  1. P Yang, A Kolbeinsson, N Shukla Deep contrastive anomaly detection for airline ancillaries prediction
    Twenty-first IEEE International Conference on Machine Learning and Applications. 2022. [PDF]
  2. N Shukla, K Yellepeddi.
    Negotiating Networks in Oligopoly Markets for Price-Sensitive Products.
    Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) WS. 2021. [arXiv]
  3. A Garg, N Shukla, L Marla, S Somanchi.
    Distribution Shifts in Airline Customer Behavior during COVID-19.
    Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) WS. 2021.
  4. A Kolbeinsson, N Shukla, A Gupta, L Marla, K Yellepeddi.
    Galactic Air Improves Airline Ancillary Revenues with Dynamic Personalized Pricing.
    Special Issue of INFORMS Journal on Applied Analytics. 2021. [PDF]
  5. A Gupta, L Marla, R Sun, N Shukla, A Kolbeinsson.
    PenDer: Incorporating Shape Constraints via Penalized Derivatives.
    Proc. 35th AAAI Conference on Artificial Intelligence. 2021. [PDF]
  6. N Shukla, A Kolbeinsson, L Marla, K Yellepeddi.
    From Average Customer to Individual Traveler: A Field Experiment in Airline Ancillary Pricing.
    Institute for Operations Research and the Management Sciences. 2020. [PDF]
  7. N Shukla.
    Dynamic Pricing for Airline Ancillaries.
    Masters Thesis, University of Illinois at Urbana-Champaign (UIUC). 2019. [PDF]
  8. N Shukla, A Kolbeinsson, K Otwell, L Marla, K Yellepeddi.
    Dynamic Pricing for Airline Ancillaries with Customer Context.
    Proc. 25th ACM SIGKDD Intl. Conf. on Knowledge discovery and data mining (KDD). 2019. [ACM-DL][arXiv][Video]
  9. A Gupta, N Shukla, L Marla, A Kolbeinsson, K Yellepeddi.
    How to Incorporate Monotonicity in Deep NetworksWhile Preserving Flexibility?
    Thirty-third Conference on Neural Information Processing Systems (NeurIPS) WS. 2019. [Workshop][arXiv][Poster]
  10. N Shukla, A Kolbeinsson, L Marla, K Yellepeddi.
    Adaptive Model Selection Framework: An Application to Airline Pricing
    Thirty-sixth International Conference on Machine Learning (ICML) WS. 2019. [Workshop][arXiv][Poster]
  11. A Kolbeinsson, N Shukla, A Gupta, L Marla.
    Leveraging Time Dependency in Graphs.
    Thirty-third Conference on Neural Information Processing Systems (NeurIPS) WS. 2019. [Workshop][PDF]

Talks

  1. A Garg, N Shukla, L Marla.
    Dealing with distribution shifts in customer choice due to COVID - 19
    Airline Group of the International Federation of Operational Research Society (AGIFORS). 2021. [Video][Slides]
  2. B Kolbeinsson, N Shukla, A Kolbeinsson.
    FLAI: Reinforcement Learning Virtual Platform for Travel
    Airline Group of the International Federation of Operational Research Society (AGIFORS). 2021. [Video][Slides]
  3. N Shukla, L Marla, K Yellepeddi.
    Deep Learning Algorithms for Dynamic Pricing of Airline Ancillaries with Customer Context
    Airline Group of the International Federation of Operational Research Society (AGIFORS). 2019. [Web][Slides]

Softwares

  1. Deep pricing© for exchange rates: Dynamic pricing solution for pricing exchange rates for reward points.
  2. Deep pricing© for ancillaries: Dynamic pricing solution for pricing ancillaries in airline industry
  3. Fluent: Deepair's internal framework for orchestrating life cycle of pricing agents. Currently powering all pricing agents deployed by Deepair Solutions.
  4. Flai: A toolkit for developing and comparing reinforcement learning algorithms. Created with Imperial College London and University of Illinois at Urbana-Champaign. [Github][Website]

Academic Projects

  1. Double Deep Q-Learning (Double DQN)
    Flappy Bird (Android game) hack using deep reinforcement learning with double Q-learning
    University of Illinois at Urbana-Champaign (UIUC). Fall 2018. [Blog][PDF][Repository][Text]
  2. Cycle Consistent Generative Adversarial Network (Cycle-GAN)
    A deep neural network based on cycle consistent image to image translation with generative adversarial networks
    University of Illinois at Urbana-Champaign (UIUC). Spring 2018. [Blog][PDF][Repository][Text]
  3. Wasserstein Deep Convolutional Generative Adversarial Network (DC-GAN)
    Deep convolutional neural network that genrates pokemons using wasserstein generative adversarial networks
    University of Illinois at Urbana-Champaign (UIUC). Spring 2018. [Tensorflow][Pytorch][Text]
  4. Handwritten Digit Recognition by Kernel PCA (Kernal PCA)
    Kernal based principal component analysis for feature extraction on hand written images provided by USPS
    University of Illinois at Urbana-Champaign (UIUC). Fall 2017. [PDF][Repository][Text][Slides][Demo]

Patents

  1. Coming soon..