Computer & Information Sciences
Data Science Challenges
Real data-science projects and challenges on Ewance — clean messy datasets, build and evaluate models, and turn raw data into decisions the way a working data scientist does. Solve them to build a portfolio of verified, recruiter-checkable proof you can do the work — not just describe it.
Recommended challenges
- CodeIntermediateNew
Generate Synthetic Tabular Data with Privacy Guarantees
Implement DP synthetic data generation: either DP-CTGAN, PATE-GAN, or a marginal-based DP method like PrivBayes / MWEM. Train on the real dataset (around 200,000 transactions, 1…
- Synthetic Data
- Differential Privacy
- Generative Models
Privacy-Preserving Machine Learning - DesignSeniorNew
Designing a Data Warehouse for a Renewable Energy Firm
You are given sample data from three sources: energy production logs, weather data, and equipment maintenance records. Your task is to: (1) design a star schema with fact and di…
- Data Warehousing
- Star Schema
- Etl
Database Systems - AnalysisIntermediateNew
Build a Bayesian Credit-Scoring Model for an Emerging-Markets Fintech
You receive an anonymized snapshot of about 30,000 historical applications with features (income proxy, tenure on platform, prior loans, region) and the binary default outcome. …
- Bayesian Learning
- Credit Scoring
- Model Evaluation
Advanced Machine Learning - ResearchIntermediateNew
Visual Question Answering for a Pediatric Radiology Workflow
You receive ~8,000 publicly available pediatric chest X-rays with structured findings labels (anonymized; no PHI access required). Build a VQA pipeline that maps a (image, quest…
- Vision Language Models
- Visual Question Answering
- Lora Finetuning
Open coursework 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
- ResearchIntermediateNew
Tune a PPO Policy for an Energy-Storage Trading Bot
You receive 18 months of 15-minute Nordic spot-price data, a battery dynamics model (capacity, round-trip efficiency, degradation curve), and a rule-based baseline that earns ab…
- Policy Gradients
- Ppo
- Reinforcement Learning
Deep Reinforcement Learning - CodeIntermediateNew
Build a Federated Learning Prototype Across Two Hospitals
Simulate two sites with non-IID data splits (one site skews older, the other younger). Implement FedAvg using Flower (or PySyft). Run for at least 50 communication rounds; repor…
- Federated Learning
- Fedavg
- Secure Aggregation
Open coursework - AnalysisIntermediateNew
Audit BLEU vs. COMET on a Multilingual Customer-Support Corpus
You receive 600 source-translation-reference triples covering 6 languages (EN as source; ES/FR/DE/JA/PT-BR/HI as targets), each scored on adequacy and fluency (1-6) by 3 profess…
- Mt Evaluation
- Neural Mt
- Statistical Analysis
Machine Translation - CodeIntermediateNew
Natural Language Inference for an HR-AI Compliance Tool
Use SNLI/MNLI/ANLI as starting data and curate 200 domain-specific HR examples (synthetic or anonymized) for fine-tuning. Fine-tune a small encoder (DeBERTa-v3-base or similar),…
- Natural Language Inference
- Transformer Models
- Fine Tuning
Open coursework - Browse challenges
Explore role
Product Manager
Ship product that solves real user problems. Combine user research, prototyping, and stakeholder alignment to turn ambiguous briefs into measurable wins — the role at the centre of modern software teams.
- ResearchSeniorNew
Open-Vocabulary Segmentation Benchmark for a Robotics R&D Lab
Use a curated 200-image household scene set (publicly-available HM3D renderings or COCO + a handful of household prompts). Benchmark 3 open-vocabulary segmentation models: SAM +…
- Open Vocabulary Segmentation
- Vision Language Models
- Benchmarking
Computer Vision - CodeIntermediateNew
Train a GNN for Fraud-Ring Detection at a Payments Fintech
You receive an anonymized transaction dataset (around 120,000 merchants, around 4 million transactions over 12 months, around 2% labeled fraud) and the team's LightGBM baseline.…
- Graph Neural Networks
- Graphsage
- Fraud Detection
Machine Learning on Graphs - CodeBeginnerNew
Build an MLP Baseline for Credit-Default Risk at a Fintech
You receive 18 months of anonymized credit-decision data (around 600,000 applications, 80 features) with a 90-day default label. Train an MLP with regularization (dropout, weigh…
- Mlp
- Regularization
- Tabular Deep Learning
Deep Learning - AnalysisBeginnerNew
Sales Performance Analysis for a 40-Person SaaS Scale-Up
You will receive a dataset containing 500+ sales opportunities with fields like deal value, stage, source, close date, and account size. Your challenge is to design a data mart …
- Data Warehousing
- Etl
- Olap
Open coursework 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
Design a Negotiation Protocol for Trading Agents
Choose a negotiation framework (alternating-offers Rubinstein, monotonic concession, or auction-based) and justify against the freight use case. Implement a simulator in Python …
- Agent Negotiation
- Game Theory
- Multi Agent Systems
Multi-Agent Systems - ResearchSeniorNew
Train Cooperative Agents with Multi-Agent RL
Pick an open multi-agent environment (PettingZoo's MPE 'simple_spread', Overcooked-AI, or SMAC). Implement or wrap three methods: IPPO (independent PPO per agent), MAPPO (centra…
- Multi Agent Reinforcement Learning
- Ppo
- Pytorch
Open coursework - DesignBeginnerNew
Build a Multi-Criteria Vendor Selection Tool for an AI Consulting Firm
You will design a Multi-Criteria Decision Analysis (MCDA, a structured way to score options against weighted criteria) tool that accepts 6-10 vendor options, 6-12 weighted crite…
- Mcda
- Decision Support Systems
- Streamlit
Open coursework - CodeBeginnerNew
Prototype a Multimodal Visual-Question-Answering Demo
You will use a small open-source vision-language model (e.g., LLaVA-1.5-7B or PaliGemma) and prompt-engineer it for the warehouse-VQA task. Build a Gradio web demo. Construct a …
- Vision Language Models
- Multimodal Perception
- Prompt Engineering
Open coursework - AnalysisIntermediateNew
Chest-X-Ray Deployment Audit Across Hospital Sites
You receive (1) a vendor-supplied multi-label chest-X-ray classifier, (2) the current single-site held-out evaluation set, (3) a 12,000-image multi-site evaluation set with 14-f…
- Medical Imaging
- Classification
- Model Evaluation
Open coursework - CodeBeginnerNew
Quantize a Vision Model for a Smart-Doorbell SoC
You receive a trained FP32 PyTorch person-detector (mAP 0.74 on a 5k validation set) plus a calibration dataset of 500 unlabeled doorbell frames. Convert to ONNX, then apply pos…
- Quantization
- Model Optimization
- Onnx
Open coursework - CodeSeniorNew
Coordinate a Fleet of Warehouse Robots
Implement a simulated warehouse grid with 80 robots solving a pick-and-deliver workload. Design a decentralized coordination protocol (recommend a contract-net or auction-based …
- Multi Agent Coordination
- Decentralized Algorithms
- Simulation
Open coursework - CodeIntermediateNew
Agentic RAG with Context-Window Budgeting
You receive a synthetic dataset of 60 founder-style queries paired with 'workspaces' (each up to 500 documents across 3 source types), plus gold-standard answers and citation li…
- Agentic RAG
- Context Window Management
- Iterative Retrieval
Retrieval-Augmented Generation - ResearchIntermediateNew
Fine-Tune a Vision-Language Model for Image Captioning
Take BLIP-2 or LLaVA-1.6 as the base. Fine-tune (LoRA is fine) on a 4,000-image accessibility-curated dataset where each image has a useful caption written by a low-vision-exper…
- Vision Language Models
- Lora Fine Tuning
- Pytorch
Multimodal Machine Learning - DesignIntermediateNew
Design Hybrid Search for an E-Commerce Product Catalog
You receive 80,000 anonymized product records (title, description, category, attributes) and a sample of 30,000 search log entries with click-through labels. Embed the catalog w…
- Hybrid Search
- Embedding Models
- Bm25
Open coursework - DesignIntermediateNew
Stand Up a Feature Store for a Series-B Fintech
Pick one priority feature group (recommend the 25 transaction-history features used by the fraud model). Define the offline source-of-truth (likely Snowflake or BigQuery), the o…
- Feature Store
- Feature Engineering
- Airflow
Open coursework - 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
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.