It contains interview preparation notes provided by iNeuron, article links.
- What is the difference between filter, wrapper, and embedded methods for feature selection? Answer
- 120 Questions. Answer
- Probability vs. Likelihood. Answer My Fav.: StatQuest
- Generative and discriminative. Answer
- ML concepts and code. Answer
- EM - Expectation-Maximization. Answer
- Random Forest. Answer
- Regression - Type of change. Answer
- Pearson vs Spearman vs Kendall: Stackexchange
- Gain and Lift Charts. listendata
- Statistical Hypothesis tests in Python. Jason
- Machine learning system design. Link
- A/B Testing. Link, Link
- Product Questions. Quora
- Random Forest to Layman. Quora
- ANOVA, ANCOVA etc. Link
- ML System Design Template Link
- PM Technical Concepts Link
- Trustworthy Online Controlled Experiments Link
- Product Sense Link
- Tableau-style User Interface for visual exploration Link
- Martin Henze (Heads or Tails). Blog
- Python Snippets. Link
- PandasVault. Link
- Python Engineer. Twitter
- Paired vs Unpaired data: link
- Data informed product building: Link
- Metric: Link, Link,SQL
- Into to Linear Algebra: Link
- IMS data sources: Link
- Predictive model performance check: ListenData
- Case Study: Link
- Collection of cases: Link, GAME
- Gradient Boosting: Link
- Federated learning: Link, Link2
- MLOps: Link
- Mixed Effect Models: Link, Link1
- ML System feature store: Link
- Data Science Cheat Sheet: Link
- Things can go wrong: Link
- Transformers from scratch Link
- Dive into Deep Learning Link
- DL Interview Link
- DL Rules of Thumb Link
- ML Forecasting Link
- MLOps without much Ops Link
- Rules of Machine Learning by Google Link
- Product Management for AI Link
- Feature Engineering and stacking Link
- Distilled AI Link
- Leetcode List link
- There is only one test Link
- Engineering Practices for DS Link
- MLE Flashcards Link
- Time Series Forecasting Link
- MLStack.Cafe Link
- Agile data science Link
- Matt Mochary Method Link
- Nubank Link
- Framework Link
- Product minded ML design. Link
- ML Design Link
- MLE Book Link
- ML System design Link
- Full stack deep learning Link
- Production Machine Learning Problems Link
- ML System Design Resources Link
- Metric Question Link
- Product Matrics Link
- ML Stack Template Link
- Patrick Halina - ML Design Link
- ML Interview Link
- ML Cheat Sheet Link
- ML Project Timelines Link
- ML in Production Link
- MLOps Paper Link
- MLOps Questions Link
- System Design Videos Link
- Instacart MLOps Link
- ML Tests Link
- Operationalizing Machine Learning Link
- Swirlai Link
- Twitter Recommendation Link
- Stanford LLM Link
- Better Product Search Link
- Natural Language Processing with Deep Learning Link
- Chat2Vis Link
- RAG vs Fine-tuning Link
Understand the business context first, don't get over-excited about the tech, and jump into coding too early. When someone asks you for a model, always ask:
👉 why do you need it?
👉 what is your current solution (e.g. what is the baseline to beat)?
👉 who is going to use the predictions and how?
👉 what is the financial impact of the model’s downtime or mistakes?
👉 which metrics do we care about to measure what?
Once you have your answers, back them up with a solid exploratory data analysis, and, when done, loop in the biz team again.
This is a critical moment as your results will translate into 3 potential outcomes:
💡 “Really? This contradicts what I thought. Well, in this case, the ML model doesn’t make much sense anymore”. You are off the hook without a single line of code 🔴
💡 “Ah, interesting. I guess we’ll have to change requirements/scope then.” Course-correct before moving forward 🟠
💡 “This is what I expected. Let’s go ahead”. Green light 🟢
“Next year, we have the opportunity to deliver $X in costs savings and revenue. Last year we delivered B projects resulting in C revenue and D cost savings. We plan to grow that by E%, requiring an F% increase in our total budget to execute.”