Skip to content

Discover your next Milestone.

Choose from industry-vetted challenges. Build local, push to GitHub, and earn cryptographic proof of your engineering skills.

Sales Forecasting with Time Series

data science & mlBeginner365d access
99onwards

Forecast product sales using Prophet and ARIMA. Build a Streamlit dashboard that visualizes predictions vs. actuals and explains seasonality and trend components.

  • Identify trend, seasonality, and stationarity in a real time series dataset
  • Train and evaluate both Prophet and ARIMA forecasting models
  • Compare model performance using MAE, RMSE, and MAPE
  • Visualize forecast results with confidence intervals in Streamlit

Customer Churn Predictor with XGBoost

data science & mlBeginner365d access
99onwards

Train an XGBoost classifier on a real customer dataset, tune hyperparameters with cross-validation, and deploy it as a FastAPI prediction endpoint.

  • Perform end-to-end ML: EDA → feature engineering → model training → evaluation → deployment
  • Train and tune an XGBoost classifier with cross-validation
  • Handle class imbalance using scale_pos_weight
  • Evaluate a classifier using precision, recall, F1, and ROC-AUC

Data Labeling Pipeline for AI Training

data science & mlBeginner365d access
99onwards

Build a pipeline that presents raw text data for human labeling via a clean UI and exports a structured JSONL dataset ready for LLM fine-tuning.

  • Design a practical data labeling schema for a real NLP classification task
  • Build a human-in-the-loop labeling tool using Streamlit
  • Export labeled data in the JSONL instruction-tuning format
  • Validate dataset quality: check for empty fields, label imbalance, and duplicates
12k+
Verified Developers
150+
Active Projects
450+
Companies Hiring
14 Days
Avg. Completion

Got questions?

Every challenge includes detailed documentation, technical constraints, and automated evaluation scripts to ensure you have everything you need to succeed.