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
- CodeIntermediateNew
Fuzz a Memory-Unsafe Image-Parsing Library
Identify 3 critical parser entry points (DICOM dataset parser, JPEG 2000 decoder, TIFF directory parser) and write a libFuzzer harness + an AFL++ harness for each. Build with AS…
- Fuzzing
- Memory Safety
- Address Sanitizer
Open coursework - DesignIntermediateNew
Threat Model a HealthTech Patient-Portal Web App
Read the 25-page redesign architecture document (auth via Clerk, Next.js front-end, FastAPI backend, Postgres, S3 for documents, webhook integration with EMRs). Build data-flow …
- Threat Modeling
- STRIDE
- Secure Design
Software Security - AnalysisIntermediateNew
Secure-by-Design Review of a Microservices Auth Subsystem
Read the 18-page proposed auth-service design (Next.js BFF, FastAPI auth-service, Postgres for sessions + refresh, Redis for short-lived tokens, integration with Auth0 for OIDC)…
- Secure Design
- OWASP Asvs
- Oauth2
Software Security - AnalysisIntermediateNew
Build a Technical Debt Register for a Legacy Banking Monolith
Run 8 structured 45-minute engineer interviews (template provided) capturing one debt item per pain point with reproducible evidence. Run SonarQube against the monolith for a qu…
- Technical Debt
- Debt Quadrant
- Code Quality
Technical Debt Management 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
- StrategyBeginnerNew
Negotiate a Technical-Debt Paydown Budget Into the Roadmap
Using the engineering debt case file, build a debt-paydown budgeting framework that fits the sprint cadence and committed work shown in the roadmap snapshot. For each of the thr…
- Technical Debt
- Stakeholder Communication
- Refactoring Budgets
Open coursework - CodeBeginnerNew
Build a Booking Web App for a Boutique Hotel Group
Design the data model (properties, rooms, availability, bookings, guests). Build the Next.js app with the App Router: 4 public pages (search, results, room detail, checkout), 1 …
- Nextjs
- React
- REST API
Web Application Development - CodeBeginnerNew
Performance Optimization for a Slow Storefront
Run Lighthouse + WebPageTest baselines on 3 representative pages (home, product detail, cart). Set up Real User Monitoring (RUM) via Vercel Analytics or web-vitals.js. Ship 5 di…
- Web Performance
- Core Web Vitals
- Nextjs
Web Application Development - CodeIntermediateNew
Multi-Tenant SaaS Backend with Postgres Row Security
Design the multi-tenant schema: shared tables with a tenant_id column, indexed appropriately. Write a forward + backward migration (using Drizzle or Prisma). Implement Postgres …
- Multi Tenant Architecture
- Postgresql
- Row Level Security
Open coursework - 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.
- CodeIntermediateNew
Secure a LoRaWAN Sensor Network for Cold-Chain Logistics
Read the LoRaWAN 1.0.x vs 1.1 spec (the network runs 1.0.3). Design the new key management: device-unique AppKey + NwkSKey, rotation every 90 days for the warehouse devices (the…
- Lorawan
- Wireless Security
- Key Management
Wireless and Mobile Networks - AnalysisIntermediateNew
Vehicle-to-Everything (V2X) Communication Trial Analysis
Load the anonymised dataset (logged packet RX/TX, PC5 sidelink RSSI, RSRP, SINR, vehicle trajectory, application latency for safety messages). Compute the canonical 3GPP Release…
- C V2x
- Pc5 Sidelink
- Wireless Performance Analysis
Open coursework - AnalysisBeginnerNew
Cellular IoT NB-IoT vs LTE-M Choice for Smart Metering
Define 6 evaluation axes: indoor / basement coverage (MCL / Maximum Coupling Loss target), battery life (15-year), data cadence (1 message every 4 hours), mobility (static), MNO…
- Nb Iot
- Lte M
- Cellular Iot
Open coursework - CodeBeginnerNew
Calibrate a Multi-Camera Rig for Warehouse Robotics
You will design and prototype a calibration workflow using a printed ChArUco board (a chessboard with embedded ArUco markers). You receive a sample dataset of 200 raw frames per…
- Camera Calibration
- Multi View Geometry
- Opencv
3D Vision and Multi-View Geometry 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
- ResearchIntermediateNew
Train a NeRF for Real-Estate Virtual Tours
You receive a curated dataset of 3 apartments, each with around 120 input images and known camera poses (already SfM-processed). Train a NeRF variant (Instant-NGP or Nerfacto re…
- Neural Scene Representation
- Nerf
- Pytorch
Open coursework - AnalysisIntermediateNew
Compare Stereo Depth Methods for a Drone Inspection Startup
You receive 500 calibrated stereo pairs from a turbine inspection plus sparse LiDAR ground truth on each pair. Implement (or wrap) three depth estimators: OpenCV Semi-Global Mat…
- Stereo Depth Estimation
- Multi View Geometry
- Model Evaluation
Open coursework - CodeIntermediateNew
Finetune a Diffusion Model for Sustainable-Fashion Mockups
You receive 1,200 product photos with paired captions and the brand's style guide. Fine-tune a Stable-Diffusion-class base model with LoRA (Low-Rank Adaptation, a parameter-effi…
- Diffusion Models
- Lora Finetuning
- Pytorch
Open coursework - ResearchSeniorNew
Benchmark Long-Context Architectures on a Legal-Doc Retrieval Task
You receive a public legal-QA dataset (e.g., LongBench's legal split or similar) filtered to documents over 50,000 tokens. Implement or wrap 3 architectures: a sliding-window Tr…
- Long Context Architectures
- State Space Models
- Transformers
Advanced Deep Learning - CodeBeginnerNew
Build a Robust Image Classifier for a Climate-Tech Satellite Startup
You receive a labeled dataset of about 25,000 Sentinel-2 patches (positive = illegal construction visible, negative = not). The dataset is split by region AND by season so you c…
- Data Augmentation
- Deep Learning
- Pytorch
Advanced Deep Learning - ResearchSeniorNew
Investigate Why Our Generative Model Memorizes Training Data
Pick a small open-source diffusion model (e.g., a Stable-Diffusion-class community model trained on LAION-subset). Reproduce a published membership-inference + extraction probe …
- Generative Models
- Memorization Analysis
- Differential Privacy
Advanced Deep Learning - 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 - CodeBeginnerNew
Stack Five Models for a Kaggle-Style Forecasting Bake-Off
You receive a pseudonymized dataset of 24 months of daily shipment volumes across about 200 origin-destination lanes plus weather and holiday features. Train 5 base models, use …
- Ensemble Methods
- Time Series Forecasting
- Feature Engineering
Advanced Machine Learning - AnalysisIntermediateNew
Structured Prediction for Insurance Claim Triage
You receive 18,000 historical claims with text, attachments-count, claim amount, customer tenure, and the ground-truth final routing bucket. Train a structured classifier (e.g.,…
- Structured Prediction
- Multi Class Classification
- Model Evaluation
Advanced Machine Learning - AnalysisBeginnerNew
Optimize Hyperparameters with Bayesian Optimization on a Tight Budget
You receive a B2B-SaaS churn dataset (about 12,000 customer-month rows, 38 features) and a fixed sweep budget of 40 trials per model family. Implement a Bayesian optimizer (Optu…
- Bayesian Optimization
- Hyperparameter Tuning
- Ensemble Methods
Advanced Machine Learning - ResearchIntermediateNew
Kernel Methods vs. Deep Learning on a Tiny-Data Drug-Discovery Task
You receive (or download) 3 public ADMET datasets from MoleculeNet (e.g., BBBP, Lipophilicity, FreeSolv). For each, train both: (a) a Gaussian process with a Tanimoto kernel ove…
- Kernel Methods
- Gaussian Processes
- Graph Neural Networks
Advanced Machine Learning - CodeSeniorNew
Train a Manipulation Policy for Bin Picking with Imitation Learning
You receive a dataset of 500 teleop trajectories on the in-distribution part plus a held-out simulation environment with a never-seen part. Train an imitation-learning policy (D…
- Imitation Learning
- Manipulation
- Diffusion Policy
Advanced Robotics
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.