Churn prediction model for a ticketing platform
Churn prediction model for a ticketing platform. Owned the model, the evaluation and the deployment. Answers are grounded in the source documents, with citations.
Loading the home page
Kavya Nair
NLP Engineer - Fine-tuning, Evaluation & LLM Apps
Rate
$82.00/hr
INAvailable for work0 contracts completedNo reviews yet
About
Fine-tuning and evaluation are where I spend most of my hours. Last quarter I fine-tuned a small open model for a Kochi health-records startup that needed on-premise extraction, matching GPT-4 accuracy on their documents at a fraction of the inference cost. I publish honest eval numbers to clients weekly, including the ugly ones.
Portfolio
03 filedSpeech-to-text pipeline for a fashion retailer
Speech-to-text pipeline for a fashion retailer. Owned the model, the evaluation and the deployment. Forecast error fell by 18% against the previous baseline.
Demand forecasting model for a pet supplies shop
Demand forecasting model for a pet supplies shop. Owned the model, the evaluation and the deployment. Forecast error fell by 18% against the previous baseline.
Reviews
No reviews in print yet
Feedback stays sealed until both sides of a completed contract have written theirs, then both are published at once. Either no contract has finished here yet, or one side is still holding its review.