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
ODE Integrator Benchmark for a Pharma PK/PD Pipeline
Use SciPy's solve_ivp + SUNDIALS (via scikit-sundae or diffeqpy) to benchmark: RK45 (baseline), LSODA, BDF (CVODE), Radau, and Rosenbrock. Run on three model classes (insulin-gl…
- Numerical Odes
- Stiff Integrators
- Scientific Python
Scientific Computing and Numerical Methods - CodeIntermediateNew
Stream-Process a 64-Microphone Array to Locate Bearing Faults in Real Time
Using the provided fixture generator and array-geometry spec, implement an overlap-add streaming pipeline that consumes 64 channels in 1,024-sample frames with 50 percent overla…
- Fft
- Signal Processing
- Beamforming
Open coursework - AnalysisIntermediateNew
Capacity Planning Model for a Black-Friday Traffic Surge
Pull 18 months of per-service request rate + utilization from Prometheus. Forecast BFCM traffic per service using a baseline + multiplicative seasonal model (Prophet or statsmod…
- Capacity Planning
- Forecasting
- Autoscaling
Site Reliability Engineering - CodeIntermediateNew
Repository + Unit-of-Work Refactor on an EF Core Codebase
Read the data-access patterns across the 5 bounded contexts (Payroll, Timesheets, Benefits, Org, Reporting) and tag the 12 worst N+1 incidents from the last quarter's traces. Au…
- Repository Pattern
- Unit Of Work
- Design Patterns
Software Design and Design Patterns 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
Design an Empirical Study of Pull Request Review Throughput
Using the provided pull request dataset and the stakeholder brief, design and run an empirical software-engineering study on review throughput. State three falsifiable hypothese…
- Empirical Software Engineering
- Software Analytics
- Statistical Analysis
Open coursework - CodeIntermediateNew
Ship an Engineering-Health Dashboard for an 18-Team Org
Using the four sample data extracts (pull-request events, Linear work-item history, PagerDuty incidents, and the quarterly developer-experience survey) and the organization brie…
- Software Analytics
- Dora Metrics
- Space Framework
Open coursework - AnalysisIntermediateNew
Diagnose a Failed Microservices Migration at a Travel Platform
Using only the four supplied materials — the interview transcript excerpts (voyalink-interview-transcripts), the decision and incident artifact corpus (voyalink-artifact-corpus)…
- Industrial Case Study
- Qualitative Research
- Software Architecture
Open coursework - DesignIntermediateNew
Design a 12-Week LeSS Rollout for Six Product Teams
Using the LeSS rules and principles source, the leadership rollout charter, the team audit and ceremony observation notes, and the team baseline metrics dataset, design a 12-wee…
- Advanced Process Models
- Scaling Agile
- Less
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.
- AnalysisIntermediateNew
Reverse-Engineer a 22-Year-Old COBOL Batch Pipeline
Use SonarQube + cobol-language tooling + JCL parsers to extract job dependencies and data-flow across the 140 jobs. Build a job-dependency graph (Graphviz). Run impact analysis:…
- Reverse Engineering
- Legacy Systems
- Dependency Analysis
Software Evolution and Maintenance - AnalysisIntermediateNew
ISO/IEC 25010 Quality Self-Assessment for a Flight-Management Module
Work only from the four materials you are given: the module technical dossier, the defect-history dataset, the customer's quality-report template, and the engineer interview not…
- Iso 25010
- Quality Assessment
- Do 178c
Open coursework - StrategyIntermediateNew
Roadmap a Defense Software Supplier from CMMI Level 2 to Level 3
Using only the materials provided to you — the de-identified Level 2 appraisal report (M1), the current-state process documentation snapshot (M2), the pilot baseline dataset for…
- Cmmi
- Process Improvement
- Process Models
Open coursework - AnalysisIntermediateNew
Defect-Trend Analysis and Quality Action Plan for an EV Charging Platform
Pull 18 months of defect data from Jira + the field-incident system + customer-service tickets. Categorize defects by component, severity, and root-cause taxonomy. Run statistic…
- Defect Analysis
- Statistical Process Control
- Root Cause Analysis
Software Quality and Process Improvement 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
- 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 - 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
Web Application Development - 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
Wireless and Mobile Networks - 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
3D Vision and Multi-View Geometry - 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
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 - 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 - CodeIntermediateNew
Implement Model Predictive Control for a Delivery Robot
You receive a kinematic bicycle model of the robot, a published track layout, and 30 minutes of recorded waypoint trajectories. Implement a nonlinear MPC controller using acados…
- Model Predictive Control
- Optimal Control
- Robotics Simulation
Advanced Robotics - CodeIntermediateNew
Localize a Mobile Robot with Particle-Filter SLAM
You receive 4 ROS bags from real customer plants, each containing 2D LiDAR scans, wheel odometry, and ground-truth poses (from a motion-capture cell used only for evaluation). I…
- State Estimation
- Particle Filter
- Slam
Advanced Robotics - CodeIntermediateNew
Build an Internal-Tools Agent for a Mid-Cap Enterprise
You receive OpenAPI specs for 4 mock internal APIs and 30 reference question-answer pairs spanning easy lookups and multi-tool chains. Build the agent using an LLM tool-use fram…
- LLM Agents
- Tool Use
- Agent Evaluation
AI Agents and LLM-Based Agents
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.