Articles by Jay
-
Delivering accuracy and explainability for AI
Delivering accuracy and explainability for AI
By Jay Nanduri
-
Our journey of applying generative AI to advance healthcare
Our journey of applying generative AI to advance healthcare
By Jay Nanduri
Activity
-
Published today in JAMA Internal Medicine - Truveta Research comparative effectiveness study on Mounjaro vs. Ozempic. Now peer-reviewed, looks at…
Published today in JAMA Internal Medicine - Truveta Research comparative effectiveness study on Mounjaro vs. Ozempic. Now peer-reviewed, looks at…
Liked by Jay Nanduri
-
Truveta Data delivers the largest and most complete mother-child EHR dataset, empowering researchers to study mothers and children through their…
Truveta Data delivers the largest and most complete mother-child EHR dataset, empowering researchers to study mothers and children through their…
Liked by Jay Nanduri
-
Our Co-founder and CTO Jay Nanduri's latest article in his series on Truveta's AI approach focuses on how we ensure that the AI technologies used in…
Our Co-founder and CTO Jay Nanduri's latest article in his series on Truveta's AI approach focuses on how we ensure that the AI technologies used in…
Liked by Jay Nanduri
Experience & Education
Volunteer Experience
-
Board of Director
Givology
- 4 years 5 months
Education
Givology: Give to learn, learn to give.
Givology (http://www.givology.com/) a 100% volunteer-run social enterprise focusing on grassroots education projects and student scholarships around the world. From teacher training and school lunch programs to library construction and scholarships emphasizing transparency and maximizing the impact on every dollar given.
Publications
-
Ecommerce Fraud Detection Through Fraud Islands and Multi-layer Machine Learning Model
Future of Information and Communication Conference FICC 2020: Advances in Information and Communication
Main challenge for e-commerce transaction fraud prevention is that fraud patterns are rather dynamic and diverse. This paper introduces two innovative methods, fraud islands (link analysis) and multi-layer machine learning model, which can effectively tackle the challenge of detecting diverse fraud patterns. Fraud Islands are formed using link analysis to investigate the relationships between different fraudulent entities and to uncover the hidden complex fraud patterns through the formed…
Main challenge for e-commerce transaction fraud prevention is that fraud patterns are rather dynamic and diverse. This paper introduces two innovative methods, fraud islands (link analysis) and multi-layer machine learning model, which can effectively tackle the challenge of detecting diverse fraud patterns. Fraud Islands are formed using link analysis to investigate the relationships between different fraudulent entities and to uncover the hidden complex fraud patterns through the formed network. Multi-layer model is used to deal with the largely diverse nature of fraud patterns. Currently, the fraud labels are determined through different channels which are banks’ declination decision, manual review agents’ rejection decisions, banks’ fraud alert and customers’ chargeback requests. It can be reasonably assumed that different fraud patterns could be caught though different fraud risk prevention forces (i.e. bank, manual review team and fraud machine learning model). The experiments showed that by integrating few different machine learning models which were trained using different types of fraud labels, the accuracy of fraud decisions can be significantly improved.
-
Microsoft Uses Machine Learning and Optimization to Reduce E-Commerce Fraud
The Institute for Operations Research and the Management Sciences
Many merchants conduct their businesses through e-commerce. One major challenge in tackling e-commerce fraud results from dynamic fraud patterns, which can degrade the detection power of risk models and can lead to them failing to detect fraud that has emerging unrecognized patterns. The problem is further exacerbated by the conventional decision frameworks that ignore the follow-up decisions made by other associated parties (e.g., payment-instrument-issuing banks and manual review agents)…
Many merchants conduct their businesses through e-commerce. One major challenge in tackling e-commerce fraud results from dynamic fraud patterns, which can degrade the detection power of risk models and can lead to them failing to detect fraud that has emerging unrecognized patterns. The problem is further exacerbated by the conventional decision frameworks that ignore the follow-up decisions made by other associated parties (e.g., payment-instrument-issuing banks and manual review agents). Microsoft developed a new fraud-management system (FMS) that effectively tackles these two challenges. It keeps features used by the machine learning (ML) risk models up to date by using real-time archiving, dynamic risk tables, and knowledge graphs. The FMS uses customized long-term and short-term sequential ML models to detect both historical and emerging fraud patterns. It also makes rapid real-time optimal decisions using a dynamic programming approach to optimize the long-term profit by taking into account the aforementioned multiple-party decisions. After implementing these innovations over a two-year period (2016–2018), Microsoft reduced its fraud loss by 0.52%, thus generating $75 million in additional savings; reduced the incorrect fraud rejection rate by 1.38%; and improved its bank authorization rate by 7.7 percentage points. The result was many millions of dollars in additional revenue. These innovations simultaneously prevent fraud and increase bank acceptance. In April 2019, Microsoft launched Microsoft Dynamics 365 Fraud Protection, a cloud-based service available for all e-commerce merchants.
-
2019 Franz Edelman Award Finalist Microsoft
The Institute for Operations Research and the Management Sciences
This podcast is part of a series highlighting the finalist teams of the 2019 INFORMS Franz Edelman Award. We will be releasing these episodes in the countdown to the INFORMS Business Analytics Conference in Austin, TX, April 14-16. In this episode, we are joined by Jay Nanduri, Distinguished Engineer, and Anand Oka, Principal Group Program Manager with Microsoft to learn how Microsoft leveraged O.R. to create a fraud detection system that identifies and reduces online fraudulent activity, while…
This podcast is part of a series highlighting the finalist teams of the 2019 INFORMS Franz Edelman Award. We will be releasing these episodes in the countdown to the INFORMS Business Analytics Conference in Austin, TX, April 14-16. In this episode, we are joined by Jay Nanduri, Distinguished Engineer, and Anand Oka, Principal Group Program Manager with Microsoft to learn how Microsoft leveraged O.R. to create a fraud detection system that identifies and reduces online fraudulent activity, while protecting legitimate consumer purchases and saving tens of millions of dollars.
Honors & Awards
-
Franz-Edelman-Laureate-2019
The Institute for Operations Research and the Management Sciences
https://pubsonline.informs.org/do/10.1287/orms.2019.02.31p/abs/
https://www.informs.org/Recognizing-Excellence/INFORMS-Prizes/Franz-Edelman-Award/Franz-Edelman-Laureates2/Franz-Edelman-Laureates-Class-of-2019
Languages
-
Hindi
Native or bilingual proficiency
-
Telugu
Native or bilingual proficiency
-
English
Full professional proficiency
Recommendations received
7 people have recommended Jay
Join now to viewMore activity by Jay
-
As #MensHealthMonth draws to a close, Truveta Research is sharing insights on prostate-specific antigen (PSA) screening recommendations, and how…
As #MensHealthMonth draws to a close, Truveta Research is sharing insights on prostate-specific antigen (PSA) screening recommendations, and how…
Liked by Jay Nanduri
-
"Perinatal women and their children have historically been excluded from clinical trials and data sources... That hinders efforts to understand the…
"Perinatal women and their children have historically been excluded from clinical trials and data sources... That hinders efforts to understand the…
Liked by Jay Nanduri
-
Recently, Truveta Research released the latest installment of their GLP-1 RA monitoring report. The report shows that overall prescription rates and…
Recently, Truveta Research released the latest installment of their GLP-1 RA monitoring report. The report shows that overall prescription rates and…
Liked by Jay Nanduri
-
Truveta offers regulatory and audit capabilities to support customers in real-world evidence submissions to the FDA and other global regulatory…
Truveta offers regulatory and audit capabilities to support customers in real-world evidence submissions to the FDA and other global regulatory…
Liked by Jay Nanduri
-
❕❕TUNE IN NOW❕❕ Dr. Nick Stucky and Tricia Rodriguez, PhD, MPH just walked through detailed methodologies and findings from three Truveta Research…
❕❕TUNE IN NOW❕❕ Dr. Nick Stucky and Tricia Rodriguez, PhD, MPH just walked through detailed methodologies and findings from three Truveta Research…
Liked by Jay Nanduri
-
⚡⚡LIVE⚡⚡ Our webinar hosts, Dr. Nick Stucky and Tricia Rodriguez, PhD, MPH, are discussing Truveta's partnerships with 30 health systems, giving us…
⚡⚡LIVE⚡⚡ Our webinar hosts, Dr. Nick Stucky and Tricia Rodriguez, PhD, MPH, are discussing Truveta's partnerships with 30 health systems, giving us…
Liked by Jay Nanduri
-
Now available via JAMA Internal Medicine: Truveta Research's study using real-world data on weight loss trends among patients with overweight or…
Now available via JAMA Internal Medicine: Truveta Research's study using real-world data on weight loss trends among patients with overweight or…
Liked by Jay Nanduri
-
Yesterday we hosted our second annual Ethics and Tech Conference where we welcomed key thought leaders from across the country to discuss the ethical…
Yesterday we hosted our second annual Ethics and Tech Conference where we welcomed key thought leaders from across the country to discuss the ethical…
Liked by Jay Nanduri
-
Looking forward to talking about "Safe and Effective AI in Healthcare: Challenges and an Approach" next week at the Seattle University 2024 Ethics…
Looking forward to talking about "Safe and Effective AI in Healthcare: Challenges and an Approach" next week at the Seattle University 2024 Ethics…
Liked by Jay Nanduri
-
Today our CTO Jay Nanduri spoke on a panel at Seattle University’s Ethics & Tech Conference about how technology can responsibly help the healthcare…
Today our CTO Jay Nanduri spoke on a panel at Seattle University’s Ethics & Tech Conference about how technology can responsibly help the healthcare…
Liked by Jay Nanduri
-
Job Alert! Truveta is #hiring an early career #fullstack #react #typescript engineer to join our Apps team… Join a great team working to make Saving…
Job Alert! Truveta is #hiring an early career #fullstack #react #typescript engineer to join our Apps team… Join a great team working to make Saving…
Liked by Jay Nanduri
People also viewed
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More