I am a Ph.D. Candidate at the Khoury College of Computer Sciences at Northeastern University, Boston, advised by Dr. Christo Wilson, studying Fairness, Transparency and Ethics in Algorithms. I strive to find answers to questions about the societal impacts of modern data driven platforms and technology's role in addressing inequality.
at the NeurIPS 2022 Workshop on Human Evaluation of Generative Models, New Orleans, USA
Avijit Ghosh, and Genoveva Fossas
at the ACM Conference on Fairness, Accountability, and Transparency (FAccT) 2022, Seoul, South Korea
Avijit Ghosh, Matthew Jagielski, Christo Wilson
at the AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2022, Oxford, United Kingdom
Avijit Ghosh, Aalok Shanbhag, Christo Wilson
at the AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2022, Oxford, United Kingdom
also presented at the Workshop on Technology and Consumer Protection (ConPro) 2022, San Francisco, California, USA (Best paper runner up)
Media articles: Propublica, Mother Jones
Piotr Sapiezynski, Avijit Ghosh, Levi Kaplan, Alan Mislove and Aaron Rieke
at the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2021, Virtual
Avijit Ghosh, Ritam Dutt, Christo Wilson
at the ACM Conference on Fairness, Accountability, and Transparency (FAccT) 2021, Toronto, Ontario, Canada / Virtual
Christo Wilson, Avijit Ghosh, Shan Jiang, Alan Mislove, Lewis Baker, Janelle Szary, Kelly Trindel, Frida Polli
at the 2nd Affinity Group Workshop on Diversity in Artificial Intelligence: Diversity, Belonging, Equity, and Inclusion (AIDBEI) at AAAI 2021
Avijit Ghosh, Lea Genuit, Mary Reagan
at the Workshop on Technology and Consumer Protection (ConPro) 2019, San Francisco, California, USA
Avijit Ghosh, Giridhari Venkatadri, Alan Mislove
at the European Conference on Information Retrieval (ECIR) 2019, Cologne, Germany (Best poster)
Ankan Mullick, Sayan Ghosh*, Ritam Dutt*, Avijit Ghosh*,Abhijnan Chakrabarty
at the WWW 2018 workshop on Exploitation of Social Media for Emergency Relief and Preparedness (SMERP) - 2018 Lyon, France
Ritam Dutt, Kaustubh Hiware, Avijit Ghosh, Rameshwar Bhaskaran
Aalok Shanbhag*, Avijit Ghosh*, and Josh Rubin*
Applied Advanced Analytics (Springer Proceedings in Business and Economics), 2021
Presented at the 6th IIMA International Conference on Advanced Data Analysis, Business Analytics and Intelligence (ICADABAI) 2019 Ahmedabad, India
Avijit Ghosh, Aditya Chourasiya, Lakshay Bansal, Abhijeet Chandra
at the Workshop on Information Technology and Systems (WITS) 2016, Dublin, Ireland.
Avijit Ghosh, Agam Gupta, Divya Sharma, Uttam Sarkar
at the European Congress of Chemical Sciences (EUCHEMS) 2018, Liverpool, UK
Avijit Ghosh, Debasis Sarkar
Avijit Ghosh*, Prerit Gupta*, Ritam Dutt, Kaustubh Hiware, Arpan Mandal, Kripabandhu Ghosh and Saptarshi Ghosh
Avijit Ghosh*, Sayan Ghosh*
• Return intership with the META (Machine Ethics, Transparency and Accountability) team at Twitter, to develop demographic agnostic metrics to measure timeline diversity.
• Working with the META (Machine Ethics, Transparency and Accountability) team at Twitter, investigating the relationship between demography agnostic and demography dependent fairness metrics at scale.
• Explain distributional shifts in Machine Learning model outputs by unifying Shapley based methods.
• Using optimal transport theory, proposed a threshold independent fairness metric that allows for real time explanations.
• Worked with the product team and civil rights lawyers in the deployment of Fiddler’s Machine Learning model fairness
dashboard. Introduced and incorporated intersectional fairness metrics in the product.
• Collaborating with PyMetrics, a talent matching software, to audit their end to end pipeline to discover and fix racial and gender biases in
their recommendation algorithm
• Analysing Fair ranking systems that have been published in CS literature and showing how they break down in the presence of noisy
protected attribute data, to show the theoretical bounds of fairness in such cases.
• Investigated Facebook’s Special Audiences system for opportunity advertisements and showed that the audience creation algorithm was
still biased against women, old people and minorites. Covered in the media by Propublica and Mother Jones.
• Analysed the ad reach and spend information obtained from Facebook’s ad transparency feature and the personal targeting dataset from
Propublica’s Facebook ad dataset and showed that advertisers with higher budgets use more privacy sensitive targeting techniques like
PII or Lookalike audiences. Findings published and presented at IEEE ConPro 2019.
• Study of how news companies promote different items on social media, investigating possible patterns of differential use.
Supervisor: Dr. Oana Goga• Worked with the smart communications team and the machine learning team at Conduent Labs (formerly Xerox Research Center India)
• Implemented XTrack, a Smart Vehicle Tracking and Battery usage minimizing Algorithm.
• Uber Surge Price Prediction using Spatio-Temporal techniques like the Neural Hawkes and Recurrent Marked Temporal Point
Process. Was given the Best Internship Project award for this project.
• Replaced the HTML XForms system used in the Android app with native generated forms using the Forms REST Api and added offline form saving.
• Configured Travis CI to automatically build and push the apk to play store.
• Automated Extraction of Catchwords from Legal Documents using a novel NER based tagger to help categorize lengthy legal texts.
• Automatically position user comments against relevant news article paragraphs. Presented at ECIR 2019.
• Savitr - A realtime location extraction system for disaster management using twitter. Presented at WWW-SMERP 2018.