Data Sciences Challenges
Explore data science challenges on Ewance to build skills employers expect from analysts and ML engineers. Work through challenges on data cleaning, exploratory analysis, modeling, and storytelling with data.
Most Popular
- AnalysisIntermediateNew
Benchmark Visual SLAM Stacks for an Indoor Delivery Robot
You receive 8 indoor rosbag recordings (about 90 minutes total) captured by the robot's stereo camera + Inertial Measurement Unit (IMU) plus ground-truth trajectories from an ex…
- Visual Slam
- Sensor Fusion
- Trajectory Evaluation
Robot Perception and Autonomy - CodeIntermediateNew
Fuse LiDAR and Camera for an Autonomous Yard Truck
You receive 6 hours of synced LiDAR + 4-camera ring data from yard operations, with 3D bounding-box labels for pedestrians, forklifts, and containers. Build a late-fusion module…
- Sensor Fusion
- Lidar Perception
- Object Detection
Robot Perception and Autonomy - CodeIntermediateNew
Design a Force-Controlled Polishing Skill for a Watchmaker
You receive simulated polishing trajectories from the manufacturer's robot, force-sensor logs from 20 master-craftsman demonstrations, and a quality-rubric (mirror finish 1-5) f…
- Impedance Control
- Force Control
- Manipulation
Robotics - CodeIntermediateNew
Scale Feature Pipelines for a Hyperscaler Search-Ranking Team
You receive a synthetic-but-realistic 80 GB sample of the ranking events plus the existing Spark pipeline (PySpark) and a Spark UI snapshot from a recent production run. Profile…
- Spark
- Distributed Systems
- Performance Profiling
Machine Learning at Scale Practice your coursework on real scenarios.
Every challenge is shaped from real-world context — not generic exercises. The work mirrors what your degree prepares you for.
Why Ewance
- DesignIntermediateNew
Build a Feature Store for a Fintech Fraud Team
You will design a feature-store layer covering 12 representative fraud features (account-level, merchant-level, transaction-level), with both batch (Spark) and online (low-laten…
- Feature Stores
- Data Pipelines
- Spark
Machine Learning at Scale - ResearchIntermediateNew
Benchmark Graph-Embedding Methods on a Climate-Network Dataset
You receive a 200M-edge sample of the knowledge graph and a labeled entity-similarity test set (5,000 pairs with relevance labels). Benchmark three methods: a shallow embedding …
- Graph Embeddings
- Graph Neural Networks
- Scalable Ml
Machine Learning at Scale - ResearchIntermediateNew
Detect Coordinated Inauthentic Behavior on a News-Sharing Network
You receive a 60-day sample of about 6 million posts mentioning a recent election, with account metadata (creation date, posting times, follower graph). Design and prototype a C…
- Network Analysis
- Anomaly Detection
- Near Duplicate Detection
Social Network Analysis and Web Science - ResearchIntermediateNew
Audit Recommender Filter Bubbles for a Civic Forum
You receive 90 days of impression logs (about 30 million recommendation events) tagged with content viewpoint labels (left-leaning, center, right-leaning, non-political) from an…
- Recommender Evaluation
- Diversity Metrics
- Audit Methodology
Social Network Analysis and Web Science - Browse challenges
Explore role
Marketing Analyst
Plan and measure campaigns that grow the business. Funnel analytics, attribution, segmentation, and the rigorous measurement that lets marketing defend its budget at the leadership table.
- ResearchIntermediateNew
Build a Generalization-Bound Tutorial for an MLE Onboarding Track
You will produce a Jupyter-notebook tutorial covering (1) sample-complexity intuition, (2) VC-dimension with worked examples for halfspaces and decision stumps, (3) Rademacher c…
- Statistical Learning Theory
- VC Dimension
- Rademacher Complexity
Statistical Machine Learning - ResearchIntermediateNew
Compare Kernel Methods to Trees on a Genomics Classification Task
You receive a curated benchmark of about 12,000 labeled variants with ~120 numerical + ~40 string features. Fit kernel SVMs (RBF, polynomial, string), random forest, and XGBoost…
- Kernel Methods
- Svm
- Tree Ensembles
Statistical Machine Learning - CodeIntermediateNew
Detect Change Points in a Trading Platform's Latency Telemetry
You receive 90 days of per-millisecond latency telemetry across 12 services, plus an incident log of 14 known regressions and 22 known false-alarm-class events. Implement and tu…
- Change Point Detection
- Anomaly Detection
- Time Series Analysis
Time Series Analysis and Forecasting - ResearchIntermediateNew
Quantify Distribution Shift for a Climate-Risk Model
You receive the model artifact (a gradient boosted regressor predicting expected annual loss per property), 2010-2020 training data, and a 2021-2024 holdout. Quantify covariate …
- Distribution Shift
- Covariate Shift
- Concept Drift
Trustworthy AI, Robustness, and Safety Build a verifiable portfolio.
Submissions become evidence. Reviewers with shipping experience score against a rubric; the result becomes a credential anyone can verify.
Why Ewance
- DesignIntermediateNew
Spec Trust-and-Safety Eval Harness for an LLM-Powered Customer-Support Bot
You will spec a 6-page evaluation harness covering: (1) jailbreak test set (about 200 prompts across 6 attack families), (2) PII-leakage probes (about 100 synthetic-customer pro…
- LLM Evaluation
- Red Teaming
- Pii Detection
Trustworthy AI, Robustness, and Safety - AnalysisIntermediateNew
Benchmark Approximate Nearest-Neighbor Indexes for a Code-Search Startup
You receive a 5 M-vector sample (768-dim, float32) and a 1,000-query labeled benchmark with ground-truth top-50 neighbors per query. Index the same sample in Chroma (HNSW), Qdra…
- Ann Indexes
- Hnsw
- Benchmarking
Vector Databases and Embeddings - CodeIntermediateNew
Lane-Change Intent Classifier from Dashcam Video
Use a public driving video dataset (e.g., Argoverse 2 sensor or BDD100K) and curate ~6,000 short clips labeled with the three-class intent. Train a temporal model (e.g., a small…
- Video Understanding
- Temporal Modeling
- Model Evaluation
Visual Intelligence and Visual Reasoning - DesignIntermediateNew
Cloud Architecture Design for a Multi-Tenant SaaS Platform
Deliver a comprehensive cloud architecture design covering: (1) Multi-tenancy strategy (shared database with row-level security vs. schema-per-tenant vs. database-per-tenant — j…
- Cloud Computing
- It Security
- Web Development
Open coursework - ResearchIntermediateNew
Seminar: Future of AI Visibility — How Brands Get Cited by ChatGPT
Research the emerging field of AI visibility / Generative Engine Optimization (GEO). Your deliverables: (1) Literature review covering at least 5 academic papers and 10 industry…
- Online Marketing
- Digital Innovation
- Academic Writing
Open coursework - AnalysisIntermediateNew
Redesign Transfer Pricing for a German Auto Supplier
Build a transfer pricing model for one EV component line (e.g., e-axle housing) flowing Germany → Hungary → Mexico → US OEM. Compare cost-plus, market-based, and negotiated appr…
- Transfer Pricing
- Managerial Accounting
- Tax Strategy
Advanced Management Accounting & Control - AnalysisIntermediateNew
Auditing Bias in a Fintech Credit Scoring Model
Conduct a quantitative fairness audit using a public proxy dataset (e.g., the UCI Adult or Give Me Some Credit dataset re-framed as BNPL decisions) and apply at least three fair…
- Algorithmic Fairness
- Ai Audit
- Regulatory Analysis
AI, Ethics and Society - AnalysisIntermediateNew
Diagnose and Restart LearnLab's Stalled Math-Tutoring Sprint
Treat the squad as a field site you can study through the records it has already produced. Using only the three provided materials, build a quantitative picture and a qualitativ…
- Scrum
- Retrospective Facilitation
- Data Analysis
Open coursework - StrategyIntermediateNew
Design a Developer Ecosystem Strategy for Tink in Southern Europe
Using the situation brief (M1), the constraints and budget sheet (M2), the developer activation-funnel dataset (M3), the interview discussion guide (M4), and Tink's public devel…
- Ecosystem Design
- Platform Strategy
- Developer Relations
Open coursework - AnalysisIntermediateNew
Channel Partner Program for a Munich Industrial Sensor Manufacturer
Your task is to create a new channel partner program. You will analyze sales data from the past 2 years (provided in a CSV with 10,000 transactions) to identify top-performing p…
- B2B Marketing
- Channel Management
- Data Analysis
Business-to-Business Marketing - AnalysisIntermediateNew
Social Preferences in a 40-Person SaaS Scale-Up
You are an internal behavioral economist at TaskFlow. Analyze the current compensation structure (50% base, 50% individual commission) and its behavioral pitfalls. Propose a new…
- Incentive Design
- Game Theory
- Social Preferences
Behavioral Economics - DesignIntermediateNew
Design a Carbon Credit Tokenization Plan for EcoToken
Working only from the materials provided to you — EcoToken's internal situation file, the registry-and-credit data extract, and the regulatory constraints brief — produce a toke…
- Blockchain
- Smart Contracts
- Solidity
Open coursework
How it works
From brief to credential, in six steps.
Step 01
Browse challenges aligned to your studies.
Step 02
Accept the one that fits your goals.
Step 03
Work through it with AI Copilot guidance.
Step 04
Submit for structured evaluation.
Step 05
Earn a verified credential.
Step 06
Add it to LinkedIn with one click.
Industry teams behind a decade of practitioner briefs
Hiring from this pool?
Sponsor a challenge and meet candidates through actual work.
Industry teams can shape briefs around the skills they hire for, then evaluate students on rubric-scored deliverables — not resumes.