Healthcare
D-Risk - MedTech Marketplace with AI Company Profiling
A three-sided marketplace linking medtech startups with investors and specialist freelancers - matched through AI document profiling.
3-sided · Marketplace model
The challenge
Early-stage medtech startups face two shortages at once: capital and the specialist expertise needed to reach the market. Bringing a medical device or diagnostic to patients means navigating market-entry research, regulatory approval, clinical-trial support and business development - each demanding scarce, expensive know-how that a small founding team rarely has in-house.
The people who can help - investors looking for credible deal flow and freelance specialists in regulatory affairs, clinical work and go-to-market - are scattered and hard to reach. Matching the right expert to a specific request usually depends on manual introductions and hand-built company profiles, which is slow and does not scale.
The approach
I built the D-Risk platform as a three-sided marketplace that brings investors, freelancers and medtech startups together in one place. Startups can raise capital and hire specialist freelancers to grow, while investors gain structured, comparable deal flow and freelancers gain a steady channel of qualified, domain-specific work.
The centrepiece is an AI information-extraction module on the startup profile. A founder uploads the company's documents; the AI reads them, extracts the key attributes of the business, and automatically assembles a structured company profile - removing the manual, error-prone step of building that profile by hand.
Those extracted attributes then drive the matching engine: when a startup posts a request - say, regulatory-approval support or clinical-trial design - the platform uses the profile to surface the freelancers whose expertise fits that specific need, across market entry, regulatory approval, clinical trials and business development.
The outcome
Results that moved the needle.
- 3-sided
-
Marketplace model
Investors, freelancers and medtech startups on a single platform
- AI
-
Automated company profiling
Documents parsed into a structured profile with no manual data entry
- 4
-
Growth support domains
Market entry, regulatory approval, clinical trials and business development
Want similar results for your project?
Every project above started with a conversation. Let's figure out what yours needs.
Keep exploring
More projects.
Rail catenary pole placement, automated
Days of expert engineering work, reduced to seconds.
Integrated LoRa Sensor Monitoring & Analytics System
Real-time monitoring and analytics for LoRa environmental sensors - from raw ingestion to geospatial drought and growth insight.
Revenue Administration MCP Server
A retrieval-only MCP server answering Turkish tax and regulation questions strictly from official government sources - zero hallucinations.
Reliability of LLMs in Safety-Critical Requirements Engineering
Master's-thesis research measuring how LLM assistance affects correctness, efficiency and trust in safety-critical requirements engineering.
DSGENAI - AI Safety Requirements Engineering Platform
Stabilising and modernising an AI-driven safety-requirements platform - Flask to Streamlit, GPT-5.1, and critical data-leak fixes.
Retrieval-Augmented Generation (RAG) Documentation Assistant
A Gemini-powered RAG assistant that turns PDF libraries into an accurate, source-grounded knowledge base.
LLM Prompt Optimization for Legal-Clause Classification
Prompt-engineering research that lifted legal-clause classification accuracy by up to 20% on Terms-of-Service documents.
Smart Contract Analysis with NLP
An NLP system that reviews business contracts and recommends changes to keep them compliant with company policy.
Football Player Potential Prediction Model
A machine-learning model that reads scouting attributes and predicts player talent level with roughly 85% accuracy.
Football Player Ranking System
An attribute-based scoring engine that ranks 750+ players and rewards standout attributes with a statistical bonus threshold.
Football Player Position Recommender System
A recommender that analyses 750+ players' attributes by position and surfaces players who would excel in an alternative role.
Automated Connecting-Flight Optimization
An automated system that recomputes viable connections across 1000+ flights the moment schedule times change.
Flight Passenger-Count Prediction
A scikit-learn regression model that predicts passenger counts per flight from operational flight features.
Turkish Image-Captioning Benchmark on MS COCO 2014
A large-scale Turkish image-captioning benchmark - 616,767 human-verified captions and five trained vision-language models.
ESG Diversity & Sentiment Solution - CFA Poland Hackathon
An ESG prototype scoring gender diversity and news sentiment - 2nd place among 44 teams from 28 universities.
Automated ESG Scoring System - HackBogazici
An automated ESG scoring engine built from four scraped data sources - 2nd place among 14 hackathon teams.