ebube.
Sports Analytics / Python & Go2025 — 2026

Slaviyy

Automated football prediction engine & expected goals (xG) analytics platform across 5 European leagues.

slaviyy.python
Core Implementation Snippet
# Slaviyy Poisson xG Probability Calculator
import scipy.stats as stats

def calculate_match_probabilities(home_xg, away_xg):
    matrix = {}
    for h in range(6):
        for a in range(6):
            prob = stats.poisson.pmf(h, home_xg) * stats.poisson.pmf(a, away_xg)
            matrix[(h, a)] = prob
    home_win = sum(p for (h, a), p in matrix.items() if h > a)
    draw = sum(p for (h, a), p in matrix.items() if h == a)
    away_win = sum(p for (h, a), p in matrix.items() if a > h)
    return {"home_win": home_win, "draw": draw, "away_win": away_win}
Markets ModeledxG, BTTS, O/U
Data IngestionAutomated CSV/API
StoragePostgreSQL
FrontendReact
Role

Full-Stack & ML Backend Developer

Timeline

2025 — 2026

Technologies
GoPythonMachine LearningPoisson DistributionPostgreSQLReactREST

Overview & Problem Solved

An end-to-end sports forecasting platform that ingests raw match fixtures and historical football data, runs statistical Poisson probability models, and delivers tiered confidence predictions (High, Likely, Risky) with data-backed reasoning.

System Architecture

Go backend for high-speed API ingestion, Python prediction worker utilizing historical dataset regression & Poisson probability distributions for expected goals (xG) and market spreads, backed by PostgreSQL and a React frontend.

Key Outcomes

  • Engineered automated match data ingestion pipeline pulling live fixtures and processing historical CSV datasets.
  • Integrated Python statistical prediction engine computing xG, BTTS, clean sheets, and over/under markets.
  • Built intuitive React dashboard displaying tiered predictions with percentage-based reasoning.