Practical learning · 9 projects
Data Science, Machine Learning and AI: projects and labs
Learn by doing: labs for each module, a project for each level, a capstone and a project exam. Every step is checked, and your work stays on this device.
Beginner
- Lab1.5 h · 4 stepsLab: a kirana shop's week of salesRead a week of sales from a kirana shop's CSV export, then answer the owner's questions: how much each category earned, what sold best, and what a typical day looks like.Not started
- Lab1.5 h · 5 stepsLab: how long do our deliveries take?A cloud kitchen wants to promise customers a delivery time. Describe one evening's 15 deliveries with the mean, median, spread and quartiles, find the outlier, and check how strongly distance and time move together.Not started
- Lab1.5 h · 4 stepsLab: A/B test of a UPI Pay buttonA payments app tried a new green "Pay now" button on half its users for a week. Add up the results, work out conversion rates and lift, run a two-proportion z-test and decide whether to ship the new button.Not started
- Lab2 h · 5 stepsLab: clean a clinic's visit registerA clinic's front desk types every visit into a spreadsheet, with all the usual mistakes. Tidy the city names, turn fee text into numbers, drop repeated rows and impossible ages, fill missing fees with the median, and report visits and average fee per city.Not started
- Project4 h · 7 stepsProject: a UPI money report for a tiffin businessSunita runs a tiffin service and is paid and pays almost everything by UPI. Turn two months of her bank app's JSON export into a report: money in and out per month, where the money goes, unusual payments and possible double payments.Not started
Intermediate
- Project5 h · 7 stepsProject: a rent model for Pune flatsA rental startup wants a fair-rent estimate for 2BHK flats in Pune. Build a linear regression from scratch: split the data, fit the line by least squares, score it against a baseline, fit it again by gradient descent, and study the errors to find what the model is missing.Not started
- Project exam1.25 h · 6 tasksProject exam: a crop adviser with k-nearest neighboursIn 75 minutes, build the model behind a farmers' helpline: read the field readings while skipping bad rows, scale the features, measure distance, predict a crop by k-nearest neighbours, score it on held-out farms and pick k by leave-one-out validation.Not taken
Expert
- Project5 h · 7 stepsProject: the retriever for a bank FAQ chatbotA bank wants a chatbot that answers only from its help-centre pages. Build the retrieval half of RAG from scratch: tokens, TF-IDF vectors, cosine similarity, top-k search, a grounded prompt that refuses when nothing matches, and a hit-rate evaluation.Not started
- Capstone10 h · 11 stepsCapstone: a scam SMS filter for a bankBuild a scam SMS filter from raw, messy data to a documented model: clean the messages, tokenise them, split them fairly, train a naive Bayes classifier from scratch, measure it with a confusion matrix, precision, recall and F1, choose the threshold on validation data, explain what the model learned and publish a model card.Not started