Design Self-Dealing Detection for Marketplaces

Read the full interview experience this question came from →

Quick Overview

This question evaluates competency in machine learning system design for fraud detection, focusing on modeling buyer–seller–item–transaction relationships, feature engineering across graph, temporal, behavioral and account-linking signals, and production concerns; it is in the ML System Design domain and emphasizes practical application and system-level architecture over purely theoretical concepts. It is commonly asked to assess a candidate’s ability to reason about data collection and labeling, model and rule trade-offs, evaluation metrics, scalability and deployment trade-offs when detecting coordinated or self-dealing activity in marketplace environments.

Design Self-Dealing Detection for Marketplaces

Company: ByteDance

Role: Machine Learning Engineer

Category: ML System Design

Difficulty: medium

Interview Round: Technical Screen

Design a machine learning system to detect self-dealing or fake transactions in an e-commerce marketplace. In this setting, a seller may use related buyer accounts to purchase their own items in order to inflate sales volume, manipulate rankings, generate fake reviews, or create fraudulent transaction history. Your design should cover: - What data you would collect. - How you would model buyer, seller, item, and transaction relationships. - What graph, temporal, behavioral, and account-linking features you would use. - Whether you would use rules, classical machine learning, graph embeddings, graph neural networks, or a hybrid approach. - How you would generate candidates and labels. - How you would evaluate the system offline and online. - How you would deploy the model and handle false positives.

Overview: This question evaluates competency in machine learning system design for fraud detection, focusing on modeling buyer–seller–item–transaction relationships, feature engineering across graph, temporal, behavioral and account-linking signals, and production concerns; it is in the ML System Design domain and emphasizes practical application and system-level architecture over purely theoretical concepts. It is commonly asked to assess a candidate’s ability to reason about data collection and labeling, model and rule trade-offs, evaluation metrics, scalability and deployment trade-offs when detecting coordinated or self-dealing activity in marketplace environments.

Read the full ByteDance Machine Learning Engineer interview experience this question came from

|Home/ML System Design/ByteDance
ByteDance logo
ByteDance
Mar 27, 2026
mediumMachine Learning EngineerTechnical ScreenML System Design
3
0

Design a machine learning system to detect self-dealing or fake transactions in an e-commerce marketplace. In this setting, a seller may use related buyer accounts to purchase their own items in order to inflate sales volume, manipulate rankings, generate fake reviews, or create fraudulent transaction history.

Your design should cover:

  • What data you would collect.
  • How you would model buyer, seller, item, and transaction relationships.
  • What graph, temporal, behavioral, and account-linking features you would use.
  • Whether you would use rules, classical machine learning, graph embeddings, graph neural networks, or a hybrid approach.
  • How you would generate candidates and labels.
  • How you would evaluate the system offline and online.
  • How you would deploy the model and handle false positives.

Submit Your Answer to Earn 20XP

Sign in to leave a comment

Loading comments...

Browse More Questions

More ML System Design•More ByteDance•More Machine Learning Engineer•ByteDance Machine Learning Engineer•ByteDance ML System Design•Machine Learning Engineer ML System Design