Back to Projects
Deep Learning · Anomaly Detection Advanced

📊 Operational Anomaly Detection System

Real-time autoencoder-based anomaly detection for flight operations data streams, with live alerting and Power BI executive dashboards.

View on GitHub
Real-time Detection
PySpark Distributed
Power BI Reporting

Project Overview

This system detects operational anomalies in real-time data streams from flight operations environments using a deep autoencoder neural network. Unlike rule-based systems, the autoencoder learns the normal behavior of the system and flags deviations automatically.

Data streams are processed at scale using PySpark for distributed computing, allowing the system to handle high-throughput operational data. The autoencoder reconstruction error is used as the anomaly score — spikes trigger immediate alerts via a Flask REST API.

Results are visualized in a Power BI executive dashboard that tracks anomaly rates, system health trends, and operational KPIs in real-time. The system was developed using domain knowledge from 10+ years of airport IT operations.

What You'll Learn

  • Build autoencoder neural networks for unsupervised anomaly detection
  • Process high-throughput data streams with PySpark distributed computing
  • Set optimal reconstruction error thresholds for anomaly scoring
  • Build a real-time alerting pipeline using Flask REST API webhooks
  • Design Power BI dashboards for executive-level operational monitoring
  • Containerize streaming ML applications with Docker

System Architecture

Data Stream
Input
PySpark
Processing
Autoencoder
TensorFlow
Anomaly Score
Threshold
Alert API
Flask
Power BI
Dashboard

Project Breakdown

01
Data Engineering

Setting up PySpark streaming pipeline, defining schemas, and handling late/out-of-order data from operations.

02
Autoencoder Design

Building encoder-decoder architecture in Keras. Choosing latent dimension size and activation functions.

03
Training & Threshold

Training on normal-only data. Using statistical methods (3σ, percentile) to set anomaly score thresholds.

04
Streaming Integration

Integrating the trained model into the PySpark streaming pipeline for real-time scoring.

05
Alerting System

Building a Flask REST API that receives anomaly events and dispatches alerts via email/webhook.

06
Power BI Dashboard

Designing executive KPI dashboards connected to the live anomaly stream via DirectQuery.