Manager - Fraud Intelligence and Analytics.Risk at MTN

Responsibilities

Fraud Pattern Discovery & Modelling


Analyse financial transaction flows (P2P, merchant payments, cash-in/out, wallet funding, withdrawals) to identify fraud patterns, typologies of unauthorized transfers, mule account networks, and high-velocity transactional attacks and any other relevant abnormal behaviours.
Translate observed fraud schemes into data-driven patterns, features, and model hypotheses.


Design and build machine-learning models to detect and predict:


Impersonation and account takeover fraud (SIM swap, social engineering, identity misuse)
Transaction laundering and agent gaming (commission abuse, float cycling, abnormal cash flows, collusive transactions)
Cyber-enabled fraud (bots, scripted attacks, app tampering)
Insider and collusive fraud patterns across users, agents, and merchants
Perform deep-dive analysis on historical fraud cases to identify emerging patterns and modus operandi
Continuously refining models based on emerging fraud trends and evolving attacker behaviour.


Advanced Analytics & Machine Learning

Develop supervised and unsupervised models for fraud detection, including:


Anomaly detection (e.g., Isolation Forest, Autoencoders, LOF)
Sequence and behaviour-based models for transaction timelines and event chains
Pattern-mining approaches to uncover recurring fraud structures
Apply statistical analysis and explainable AI techniques to interpret model outputs and support operational decisions.
Evaluate model performance using appropriate fraud metrics (precision, recall, false positives, financial impact).


Transaction Data Analysis & Feature Engineering

Engineer predictive features from multi-source financial and behavioral data:


Transactional features: amount, frequency, velocity, time-of-day patterns, beneficiary history, geographic mismatch flags.
Device & network intelligence: IMEI/IMSI/ICCID associations, device fingerprinting, VPN/proxy detection, IP reputation, location spoofing signals.
Behavioral biometrics: typing dynamics, navigation patterns, session timing, interaction cadence.


Risk Engine Integration & Decision Systems


Design scoring frameworks and decision logic for production risk engines, blending model scores with rule-based signals.
Define and calibrate risk thresholds, alert triggers, and automated actioning (block, step-up auth, review).
Implement and optimize real-time fraud controls such as geo-fencing, velocity checks, SIM-swap logic, and session risk scoring.


Qualifications

Education


Bachelor's degree in computer science, Data Science, Statistics, Mathematics, or a related field.
MBA and/or master's degree is advantageous
Preferred: Master's degree in data Analytics, Machine Learning, or Cybersecurity


Experience


5 years or more experience in fraud analytics, data science, or risk modeling roles
At least 3 years' experience within a non-traditional FinTech /ICT/Digital/Fraud Management environment
Proven track record of building and deploying ML models for fraud detection


Apply Before 03/18/2026