Akshata Kishore Moharir

About Me

I am a seasoned Lead Data Scientist with 10+ years of experience, dedicated to transforming complex business challenges into innovative solutions across diverse industries such as Support, Gaming, Retail, Aviation, Education, and Transportation.

My AI/ML Journey

Experience

My journey in the realm of data science has equipped me with extensive expertise in Generative AI, Responsible AI practices, Predictive Modeling, Explainable AI, Natural Language Processing, Fraud Detection, and Predictive Maintenance.

Lead Data Scientist

I am responsible for developing and leading Generative AI & ML efforts to identify and mitigate Fraud by building Human in Loop Transparent and Responsible AI models.

Microsoft

Oct 2022 - Present

Principal Data Scientist

Developed Machine Learning models at Scale for predictive maintenance & Delay prediction for trains.

Amtrak

Mar 2022 - Oct 2022

Senior Data Scientist

I was responsible for developing Human Centered Machine Learning Services which help in making the AI/ML models transparent by bridging the gap between the Domain Experts and Black Box AI /ML models, productionization of Machine Learning Platforms as a Service, developing next generation Airplane Health Management services and Prognostics and Health management of Aircraft

Boeing

Aug 2016 - Aug 2020

Data Scientist

Responsible for designing and implementing processes and layouts for complex, large-scale data sets used for modeling, data mining, and research purposes.

Harman International

Jan 2015 - Apr 2016

Education

Oct 2022 - Present

Masters Of Science, Analytics

University of Maryland College Park

Bachelors of Engineering, Computer Science

Visvesvaraya Technological University

Aug 2016 - Aug 2020

Analyzing

In a wide range of subject areas, I have analyzed structured and unstructured data to extract actionable business insights. I love to craft stunning and clever visualizations that illustrate surprising results.

Developing

I’m strongly convinced that machine learning models should not go to waste in Jupyter Notebooks. Using my software engineering skills, I’ve built and deployed AI services which create real business value.

Communicating

I enjoy public speaking, writing professional articles, sharing my knowledge and discussing diverse topics. Thanks to my training and experience in science communication, I’m able to present complex results to a non-technical audience.

Publications

Conference, Workshops/Poster Presentation

Presented at 2024 ICML on “Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy” Presenting at 2024 NeurIPS on : “Towards Commercialization of Tokamaks: Time Series Viewmakers for Robust Disruption Prediction”
Presented at IEEE CONNECT conference on “Explainable and visually interpretable machine learning for flight sciences”
Presented at IEEE INOCON conference on “Learning Interpretable Rules
Contributing to Maximal Fuel Rate Consumptions in an Aircraft using Rule Based Algorithms”
“Comparison of Diagnostic machine learning models with physics-based models for predicting the lithium-ion battery degradation behavior “presented at IEEE WinTechCon, 2018
Presented at 13th WIML conference (NeurIPS: Dec 2018) on “Application Hybrid Extreme Rotation Forests on aircraft Predictive Maintenance”
Paper “Fault prediction in aircraft engines using Regularized Greedy Forests” presented at National Machine learning and artificial intelligence conference hosted by IIM Bengaluru.
Paper “Application of Rotation Forest for Aircraft Engines Fault Diagnosis “presented for International Conference on Business Intelligence hosted by IIM, Bengaluru, IISC, Bengaluru.
Presented at Women in Data Science conference 2018 hosted by American statistical association on “Deep learning-based approach for Competitor analysis”, Ohio.

Patents

U.S. Patent: Granted, 20220121988, “Computing platform to architect a machine learning pipeline”, April 21, 2022.
U.S. Patent: Granted, 11263480, “Machine learning model development with interactive model evaluation,” March 1, 2022.
U.S. Patent: Granted, 20210118242, “Predicting a repair and maintenance activity for an aircraft system”, April 22, 2021.
U.S. Patent: Granted, 20200293940, “Machine learning model development with interactive model building,” April 30, 2020.
U.S. Patent: Granted, 20200134367, “Interactive machine learning model development”, April 30, 2020.
U.S. Patent: Granted, 20200134368, “Machine learning model development with interactive exploratory data analysis,” April 30, 2020.
U.S. Patent: Granted, 20200134369, “Machine learning model development with interactive feature construction and selection”, April 30, 2020.