This proposal can help Marketers and Content Creators understand which type of content engages well with users (indicated by views, clicks, etc). It uses topic models to convert long-form articles into tags and provide a snapshot view of content tags to such engagement metrics.

Outcomes: 

• Presented in Adobe Sneaks 2021  [Video Link]

• Media Coverage in Forrestor, Fast Company, and Adobe Blogs [one, two]

• Also adapted the method for Creatives - [Video Link]

• US Patent granted. 

Adobe Sneaks is a highly-selective projects shown in Adobe Summit as next-generation customer experiences in Adobe. 

Topic Models     Image Tagging    Readability

This proposal proposes to keep articles evergreen such that they resonate and remain relevant to readers through personalized examples. Using LLMs, it changes an example according to user topic interest, geographic region, or even generation. 

Outcomes: 

• Accepted at NeurIPS Workshop, 2023 [Poster] [Paper] [Website]

• Presented at Adobe GenAI Internal Hackathon [Video Link]

• US Patent filed. 

Large Langauge Model    Fact-Checking    Information Extraction

This proposal enables creatives to assign ad-hoc tasks to others within their network, based on profiles, availability, task preferences, and past interactions. It streamlines the tracking and communication process, alleviating the burden from creatives.

Outcomes: 

• Presented in Adobe Hackathon  [Video Link] 

Topic Models     Profile Matching   Load-Balancing

Problem: Content marketers often rely on manual research to understand which content strategies work, leading to repetitive approaches like "how-to articles" that fail to engage customers effectively.
Solution: To address this, I proposed the Content Tensor, an AI-powered tool that analyzes existing content and visualizes it by strategy, topic, and engagement. The tool is designed to help markters quickly identify gaps in content (blog ideas)  by showing successful or under-utilized strategies across topics. I led this initiative from identifying the market opportunity, prototyping ML-backend and XD demos, and finally presenting it to Senior VPs at Adobe.

Outcomes: 

• One of Seven projects to be selected from 117 submissions for Semi-Finals of Adobe Sneaks 2022  [Video Link]

Adobe Sneaks is a highly-selective projects shown in Adobe Summit as next-generation customer experiences in Adobe. 

Few-Shot Classification