NAR Sistem Teknoloji
Back to Products
S

SEIDRA

ML-Powered Theft Detection

ML-powered electricity theft detection and scoring platform for Turkish electricity distribution companies (EDAŞ). Ingests subscriber data, meter readings, OBIS events and inspection history to produce explainable theft probability scores (0-100) per subscriber, enabling field teams to prioritize non-technical loss inspections with 3x+ hit rate improvement.

Request Demo for SEIDRA

Key Features

3-layer ML architecture: Base Model (XGBoost), OSOS Head (XGBoost + LSTM + Rules), Boost Head
100+ features across 8 categories: power triangle, per-phase, load profile, tariff integrity and more
LSTM autoencoder pattern transfer — learns consumption signatures of tamper-flagged meters
SHAP-based explainability with natural language Turkish explanations per suspect
Configurable OBIS catalogue with 30+ entries and per-manufacturer bitmask definitions
Graph analytics (PostGIS) for fraud cluster detection and geographic correlation
Multi-DB adapter framework (Oracle, PostgreSQL, MSSQL, MySQL) with REST and CSV ingestion
3x+ inspection hit rate improvement over random targeting, auditable model lifecycle

Modules

I
ING

Data Ingestion — Multi-DB adapter framework (Oracle, PostgreSQL, MSSQL, MySQL), REST API for OSOS data, CSV bulk import and DLMS/IEC 62056-21 parser

O
OBI

OBIS Catalogue — 30+ configurable entries, per-manufacturer bitmask definitions and admin UI for editing and discovery

F
FEA

Feature Engineering — 100+ features across 8 categories: power triangle, per-phase, load profile, demand, tariff integrity, comms/time, transformer balance and peer comparison

M
ML

3-Layer ML Architecture — Base Model (XGBoost), OSOS Head (XGBoost + LSTM + Rule Engine) and Boost Head (sparse XGBoost) with staging and promotion

P
PAT

Pattern Transfer — LSTM autoencoder learning consumption patterns of tamper-flagged meters to identify sophisticated theft in unflagged subscribers

E
EXP

Explainability — SHAP-based feature attribution with natural language Turkish explanations and confidence levels (LOW/MED/HIGH/VERY_HIGH)

I
INS

Inspection Workflow — Prioritized subscriber list, drill-down profiles, inspection order creation, field team dispatch and feedback loop

G
GRA

Graph Analytics — PostGIS-based fraud cluster detection, geographic correlation and network-level theft pattern analysis