All projects

Other

Football Player Position Recommender System

A recommender that compares a player's attribute profile against the profiles of other positions and finds players could be more valuable in a different role.

Scoutium Recommender System Development
Data Science Machine Learning Python Recommender Systems Scouting Sports Analytics
Football Player Recommender System

The challenge

A player is almost always watched in the position they already play, and judged by that position's criteria. That carries a hidden cost: a centre-back whose attribute profile would actually make him a good defensive midfielder can spend a career labelled "average" as a centre-back.

Searching for these matches by hand isn't practical. With 277 players and 10 positions, evaluating every player through every position's lens means thousands of comparisons - and a scout's time already goes to watching the match.

Scoutium wanted to see these opportunities systematically: not how good a player is, but where else they might be better.

The approach

I built a system that analyses player attributes per position and recommends cross-position fits.

  1. I derived an attribute signature for each position. The data was segmented by position and I identified which attributes score highly among players considered successful in each role. The result is a profile per position: "being good in this role means being strong on these attributes."
  2. Every player was evaluated outside their own position too. A player's 39-attribute profile was compared not against their current position's signature but against the others'. Alongside "how good is this player in their current role" came a second question: "which other role's profile do they fit?"
  3. Strong matches are surfaced. Where a player's profile clearly fits the signature of a position they don't play, the system flags it as a recommendation - for example a centre-back whose attributes overlap with the defensive-midfielder profile.
  4. The decision stays with the scout. The system doesn't decide transfers or position changes; it lists candidates worth examining. The scout then watches the player with that possibility in mind.

The value of this approach is that it extracts new information from existing data: the same scout scores answer a second question without collecting anything new.

Stack: Python, pandas; position-segmented attribute analysis, profile comparison and cross-position matching.

Want similar results for your project?

Every project above started with a conversation. Let's figure out what yours needs.

Keep exploring

More projects.

Other · A rail infrastructure engineering firm

Rail catenary pole placement automation

Weeks of expert engineering work, reduced to seconds.

View
Healthcare · Decoto International

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.

View
Technology · Ottronic E-Systems (TUM 1000+ Project Week)

Integrated LoRa Sensor Monitoring & Analytics System

Turning raw LoRa telemetry from tree-mounted sensors into live dashboards that answer watering and growth questions - built in one week.

View
Other · A certified accountant

Revenue Administration MCP Server

An assistant that reads Turkish tax legislation from its official source at the moment you ask and answers with the article behind it - a system a certified acc

View
Technology · Fraunhofer IKS, Munich

Reliability of LLMs in Safety-Critical Requirements Engineering

A controlled experiment measuring what an ungrounded, off-the-shelf chatbot contributes to safety-critical engineering.

View
Technology · Fraunhofer IKS, Munich

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.

View
Technology · Independent project

Retrieval-Augmented Generation (RAG) Documentation Assistant

A RAG assistant that turns stacks of PDFs into a searchable knowledge base where every answer traces back to the source document.

View
Technology · Technical University of Munich

LLM Prompt Optimization for Legal-Clause Classification

Comparative research that lifted F1 from 0.62 to 0.76 on Terms-of-Service clause classification through automatic prompt optimisation alone - without retraining

View
Technology · Siemens

Smart Contract Analysis with NLP

An NLP system learns from Siemens' legal team's past contract revisions, flags the same clauses in a new contract, and proposes the edit that was made before.

View
Other · Scoutium

Football Player Potential Prediction Model

A classification model predicting whether a player will be marked "highlighted" from 39 scout attribute scores - ROC-AUC 0.86 under 10-fold cross-validation.

View
Other · Scoutium

Football Player Ranking System

A scoring engine that ranks players not by total score, but by how many attributes they exceed the statistical average for their own position.

View
Other · Turkish Airlines

Automated Connecting-Flight Optimization

A tool that recalculates every connection possible through the hub - day by day, with passenger volumes - when a single flight's time is shifted.

View
Other · Turkish Airlines

Flight Passenger-Count Prediction

A demand model predicting booked passengers on one-stop routes from a flight's own characteristics, selected by comparing eleven regression models.

View
Technology · Istanbul Bilgi University

Turkish Image-Captioning Benchmark on MS COCO 2014

A human-verified Turkish caption dataset covering all of MS COCO, plus five models trained on it - a new reference point for Turkish image captioning.

View
Finance & Fintech · CFA Poland (hackathon)

ESG Diversity & Sentiment Solution - CFA Poland Hackathon

An ESG prototype scoring gender diversity and news sentiment - 2nd place among 44 teams from 28 universities.

View
Other · Boğaziçi University IT Club (hackathon)

Automated ESG Scoring System - HackBogazici

An automated ESG scoring engine built from four scraped data sources - 2nd place among 14 hackathon teams.

View