Research that keeps actuarial ML honest in time

Muskan Sharma — Main Researcher, Research Programmer, and Scientist at Data-T — leads FEATSRV and FeatLock 1.0: leakage-free point-in-time feature serving, open papers, and production-ready APIs for insurance MLOps.

Muskan Sharma

Main Researcher · Research Programmer · Scientist · Data-T Quantum & Actuarial Research

Designs and ships end-to-end research systems — from temporal theory and synthetic benchmarks to FastAPI surfaces and operator consoles — so actuarial models train and serve on the same leakage-free feature definitions.

Latest work

Complete programme for Muskan Sharma — research papers, technical blogging, and APIs — newest first.

Top research capabilities

Muskan Sharma advances Data-T research through point-in-time stores, Redis online serving, leakage science, and open engineering reports.

FEATSRV

Lead research platform for leakage-free actuarial feature serving.

PIT

FeatLock 1.0™

Operator console and API surface for online, offline, and audit workflows.

1.0

Online Redis

Sub-10 ms policy and claim feature lookups for real-time scoring.

<10 ms

Open science

Zenodo archive and reproducible Nimbus fixtures for peer review.

OA

Research blogging

Figure-led explainers on lineage, leakage, importance, and latency.

Blog

MLOps APIs

Same-origin /api/featlock proxy to FastAPI health, PIT, and audit routes.

REST

Key contributions

Scientific and engineering highlights from Muskan Sharma as main researcher and research programmer.

Point-in-time correctness

Formalised valid-time as-of joins for SCD Type 2 actuarial entities so historical training sets never see future address, claim, or policy state.

Dual join engines

Delivered Feast/Dask and PySpark SQL PIT paths with byte-identical regression checks for interactive and portfolio-scale workloads.

FeatLock 1.0 console

Shipped the operator-facing dashboard — overview, lineage, risk & leakage, feature importance, PIT training, and online Redis lookups.

Nimbus benchmark

Designed seven intentional leakage-trap packs so researchers can prove unguarded joins inflate metrics before production.

REST serving surface

Authored FastAPI routes for /health, /online/*, /offline, /pit-training, /leakage-audit, and /feature-importance with x-api-key auth.

Research programming

Bridges actuarial science and software engineering — reproducible notebooks, CLI service packs, and open-access Zenodo reporting.

Smarter impact powered by Data-T research

Data-T Research · Muskan Sharma

Connect on leakage-free feature serving and actuarial MLOps

Papers, FeatLock APIs, and open-source research programming from Data-T.

Email dt@data-t.uk

Stay connected

What's New at Data-T — updates from Muskan Sharma's research programme, FeatLock releases, and papers.