Back to Dashboard

SO-AI

API Running

Concert Demand Forecasting System

AI-Powered Ticket Demand Prediction

Concert ticket demand forecasting system using machine learning and large language models (LLM). Analyzes social media, news, historical data, and trends for accurate sales prediction.

OpenAI GPT Integration
Spotify & YouTube API
Real-time Social Sentiment

BREAKING NEWS LIVE

Loading news...

ARTIST SEARCH

INSIGHTS

Loading insights...

Live Prediction

Enter event details

Prediction Result

Enter artist details and click "Predict Demand"

System Modules

Data Pipeline

Data collection from multiple sources: Spotify, YouTube, social media, news sites, ticket platforms.

Collectors Processors Storage

AI Integration

LLM integration (OpenAI, YandexGPT, Google Gemini) for sentiment analysis and event extraction from news.

LLM Analyzer Sentiment News Parser

ML Model

Machine learning models (CatBoost, XGBoost, LightGBM) for demand forecasting and sellout probability.

Predictor Trainer Features

FastAPI Server

REST API for predictions, artist analysis and real-time report generation.

/predict /artist /top

Streamlit Dashboard

Interactive dashboard for visualizing predictions, top artists and historical analysis.

Plotly Charts Reports

Scheduler

Task scheduler for automatic data updates, model retraining and monitoring.

Celery Cron Monitoring

Data Flow Architecture

Spotify API
YouTube API
Social Media
News Sources
Smart Data Collector
AI-enhanced data pipeline
LLM Analyzer
GPT / YandexGPT
Feature Engineering
200+ features
ML Predictor
CatBoost Ensemble
Demand Score
0-100
Sellout Probability
%
Sellout Time
hours/days

Key Features

Sentiment Analysis

Comment sentiment analysis using LLM. Identifies categories: excitement, criticism, question, neutral. Evaluates purchase intent.

{
  "sentiment_score": 8.5,
  "intent_to_buy": true,
  "category": "excitement",
  "buy_intent_percentage": 67%
}

News Event Extraction

Extracting significant events from news: album releases, tour announcements, scandals, awards. Impact assessment on popularity.

{
  "event_type": "album_release",
  "impact_score": +8,
  "confidence": 0.95
}

Demand Prediction

Demand prediction based on 200+ features. Uses ensemble of CatBoost + XGBoost models for maximum accuracy.

{
  "demand_score": 85,
  "sellout_probability": 92%,
  "estimated_time": "<24 hours"
}

AI Market Reports

Automatic generation of analytical reports with recommendations for promoters and secondary market forecasts.

1. Executive Summary
2. Strengths
3. Risks and Limitations
4. Recommendations
5. Secondary Market Forecast

API Endpoints

POST /predict Concert demand prediction
GET /artist/{name} Detailed artist analysis
GET /top-artists Top artists by demand
GET /health System status check

Required API Keys

OPENAI_API_KEY
GPT-4 for analysis
SPOTIFY_CLIENT_ID/SECRET
Popularity data
YOUTUBE_API_KEY
Views and trends
TWITTER_BEARER_TOKEN
Social analysis
VK_ACCESS_TOKEN
VK analysis
POSTGRES_URL
Database

Ready to Start?

Project is ready for development. Choose an action:

Back to Dashboard
QS: 0 S: 0 IV: 0 TT: 0