Topfolio
www.topfolio.in

Data Scientist - Work Experience

Full 8-week curriculum

2 Months1-2 hrs/day (more during the deployment + capstone weeks)Advanced → Job-Ready₹6,999 one-time
◆ WHAT'S INSIDE

Everything you'll learn, build, and use.

8
skills
7
tools
5
portfolio projects
WHAT YOU NEED TO START
  • Solid SQL + Python and basic analytics comfort - this is not a beginner program (that's Data Analyst - Advanced)
  • 1-2 hrs/day for the full 8 weeks
Everything else is taught inside — Statistical rigor - from Week 1, resources land with each task · ML from scratch - no prior ML needed · MLflow, FastAPI, Docker · RAG & vector stores. Resources land with each week's task.
SKILLS YOU'LL ADD
Statistical reasoning you can defendA/B testing (power, SRM, Bayesian readouts)ML modeling on messy dataFeature engineering & honest evaluationExperiment tracking with MLflowModel deployment (FastAPI + Docker)Retrieval-augmented generation with evalsMethodology writing & interview defense
Each skill comes with a curated video course when the task needs it — how it works
TOOLS YOU'LL USE⚙ Python (scikit-learn, pandas)⚙ SQL⚙ MLflow⚙ FastAPI⚙ Docker⚙ pgvector⚙ AI copilots
◆ PORTFOLIO PROJECTS YOU'LL SHIP
WK 1-2
A/B test analysis with exec summary
Power + sample size, frequentist + Bayesian, written exec-style.
WK 3-4
Churn/LTV model on messy data
Imbalance handled, AUC/PR, threshold tied to business ROI.
WK 5-6
End-to-end ML pipeline deployed live
MLflow → FastAPI /predict → Docker → a demo anyone can hit.
WK 7
An evaluated RAG app
Citations + a basic hallucination check.
WK 8
Polished GitHub portfolio
A methodology write-up per project, interview-ready.
◆ 8-WEEK BREAKDOWN

What you'll ship, week by week.

WEEK
1
Statistics & Experimentation Foundations
◆ SHIPS
Week 1
↳You'll arrive with: The entry bar: solid SQL + Python and analytics comfort. The statistical rigor is what this week builds — resources land with the task, like every week.
WHAT YOU'LL DO
  • ▸Distributions, sampling & uncertainty
  • ▸Hypothesis testing done right
  • ▸Confidence intervals you can defend
  • ▸Where analysts' stats intuition breaks
SKILLS YOU'LL ADD
Reason about distributions, sampling & uncertaintyRun hypothesis tests correctlyDefend a confidence interval
Curated learning resources land with this week's task.
TOOLS⚙ Python⚙ SQL
◆ YOU SHIP THIS WEEK
Project 1 begins: the statistical groundwork for a defensible A/B analysis
Reviewed in Discord · written feedback within 24h
WEEK
2
A/B Testing the Way It's Actually Tested
◆ SHIPS
Week 2
↳You'll arrive with: Working statistical instincts from Week 1.
WHAT YOU'LL DO
  • ▸Power & sample-size before you launch
  • ▸Frequentist + a Bayesian readout
  • ▸SRM, peeking & novelty effects
  • ▸Writing the experiment readout exec-style
SKILLS YOU'LL ADD
Compute power & sample size before launchRead out frequentist + Bayesian resultsCatch SRM, peeking & novelty trapsWrite an exec-style experiment readout
Curated learning resources land with this week's task.
TOOLS⚙ Python
◆ YOU SHIP THIS WEEK
Project 1 ships: a full A/B test analysis with exec summary + appendix
Reviewed in Discord · written feedback within 24h
WEEK
3
ML Modeling on Messy Data
◆ SHIPS
Week 3
↳You'll arrive with: A shipped experiment analysis and the stats to defend it.
WHAT YOU'LL DO
  • ▸Framing a business problem as a model
  • ▸Baselines first, always
  • ▸Handling leakage, drift & messy joins
  • ▸Choosing the right model for the job
SKILLS YOU'LL ADD
Frame a business problem as a modelBuild honest baselines firstHandle leakage, drift & messy joins
Curated learning resources land with this week's task.
TOOLS⚙ Python (scikit-learn, pandas)⚙ SQL
◆ YOU SHIP THIS WEEK
Project 2 begins: a churn/LTV model on genuinely messy data
Reviewed in Discord · written feedback within 24h
WEEK
4
Feature Engineering & Honest Evaluation
◆ SHIPS
Week 4
↳You'll arrive with: A working baseline model from Week 3.
WHAT YOU'LL DO
  • ▸Feature engineering that moves the metric
  • ▸Imbalanced data: precision/recall/AUC/PR
  • ▸Calibration & threshold tied to a business decision
  • ▸Ship a churn/LTV model end-to-end
SKILLS YOU'LL ADD
Engineer features that move the metricEvaluate imbalanced data (precision/recall, AUC/PR)Tie thresholds to a business decision
Curated learning resources land with this week's task.
TOOLS⚙ Python (scikit-learn)
◆ YOU SHIP THIS WEEK
Project 2 ships: the churn/LTV model, evaluated in business terms
Reviewed in Discord · written feedback within 24h
WEEK
5
Notebook → Tracked, Packaged Model
◆ SHIPS
Week 5
↳You'll arrive with: A model you can defend — this week it becomes reproducible.
WHAT YOU'LL DO
  • ▸Reproducible training runs
  • ▸Experiment tracking with MLflow
  • ▸Packaging a model for handoff
  • ▸Versioning data + model together
SKILLS YOU'LL ADD
Make training runs reproducibleTrack experiments with MLflowVersion data + model together
Curated learning resources land with this week's task.
TOOLS⚙ MLflow⚙ Python
◆ YOU SHIP THIS WEEK
Project 3 begins: your model, tracked and packaged for handoff
Reviewed in Discord · written feedback within 24h
WEEK
6
Ship It Live
◆ SHIPS
Week 6
↳You'll arrive with: A tracked, packaged model from Week 5.
WHAT YOU'LL DO
  • ▸Wrap the model in a FastAPI /predict
  • ▸Containerize with Docker
  • ▸A demo anyone can hit
  • ▸Latency, cost & failure thinking
SKILLS YOU'LL ADD
Serve a model behind a FastAPI /predictContainerize with DockerReason about latency, cost & failure
Curated learning resources land with this week's task.
TOOLS⚙ FastAPI⚙ Docker
◆ YOU SHIP THIS WEEK
Project 3 ships: your ML pipeline deployed live, demo anyone can hit
Reviewed in Discord · written feedback within 24h
WEEK
7
Applied GenAI - an Evaluated RAG App
◆ SHIPS
Week 7
↳You'll arrive with: You've deployed a real ML system — GenAI starts from zero here.
WHAT YOU'LL DO
  • ▸Embeddings & a vector store
  • ▸Retrieval + citation over your own docs
  • ▸A basic hallucination / faithfulness check
  • ▸Where GenAI fits a DS toolkit (and where it doesn't)
SKILLS YOU'LL ADD
Build retrieval over your own documentsGround answers with citationsCheck faithfulness & hallucination
Curated learning resources land with this week's task.
TOOLS⚙ pgvector⚙ Python
◆ YOU SHIP THIS WEEK
Project 4 ships: an evaluated RAG app with citations
Reviewed in Discord · written feedback within 24h
WEEK
8
Capstone Hardening & Mock Loop
◆ SHIPS
Week 8
↳You'll arrive with: Four shipped projects. This week they become a portfolio you can defend.
WHAT YOU'LL DO
  • ▸Defend every modeling trade-off
  • ▸Polish the GitHub portfolio + READMEs
  • ▸A methodology write-up per project
  • ▸Mock DS interview on your own work
SKILLS YOU'LL ADD
Defend every modeling trade-offWrite a methodology doc per projectInterview on your own work
Curated learning resources land with this week's task.
TOOLS⚙ GitHub⚙ Docs
◆ YOU SHIP THIS WEEK
Project 5 ships: a polished GitHub portfolio + methodology write-ups
Reviewed in Discord · written feedback within 24h
◆ HOW IT RUNS

Yes, you get videos. Yes, you get live time — but neither is the program; the work is. Real tasks with deadlines · a curated video course per skill, watched when the task needs it · AI as your pair-worker, reviewed so you understand every line · written review of every submission within 24 hours · a personal weekly 30-min 1:1. Full details →

₹6,999 one-time · pause anytime · lifetime access
See the program & enrollAsk Anuj on WhatsApp
Data Scientist - Work Experience - Full 8-Week Curriculum & Brochure