Subjects

Decision Trees

Learn how decision trees partition feature space using impurity measures, how recursive binary splitting works, which hyperparameters control overfitting, and how feature importance is calculated — the foundation for understanding gradient boosting models like LightGBM and XGBoost.

LightGBM

Understand how LightGBM builds sequential ensembles of trees, why leaf-wise growth outperforms level-wise, what every key hyperparameter controls, why a slow learning rate with more trees generalizes better, and how to diagnose and fix overfitting through regularization.

LLM Application System Design

Learn to design LLM-powered systems for interviews and production: prompt vs RAG vs fine-tuning, end-to-end RAG architecture, token and cost budgeting, evaluation, guardrails, agents, caching and routing, with a worked support-assistant design.

ML System Design Interview Framework

Learn how ML system design interviews are scored, a 7-step framework from requirements to monitoring, back-of-envelope estimation for QPS, embeddings and GPU cost, common problem framings, and the mistakes that sink strong candidates.

Case Study: Video Recommendation (YouTube / Netflix-style Homepage)

Walk through a model ML system design interview answer for a video recommendation homepage: objectives, implicit-feedback labels, two-tower retrieval, multi-task ranking, position bias, cold start, evaluation, A/B testing, serving at scale, and monitoring.

Ranking & Recommendation System Architecture

Learn the multi-stage recommendation architecture: candidate generation with two-tower models and ANN search, pointwise/pairwise/listwise rankers, multi-task value formulas, position debiasing, cold start, re-ranking policy, and how offline metrics relate to online A/B results.

Model Serving & Deployment

Learn to design the serving side of an ML system: batch vs online vs streaming vs hybrid inference, latency budgets with numbers, model server patterns, compression, canary and shadow rollouts, feature-store consistency, autoscaling, and safe fallbacks.

Clustering & Dimensionality Reduction

Learn k-means, hierarchical clustering, DBSCAN and Gaussian mixtures, how to choose k and evaluate clusters without labels, and how PCA, t-SNE and UMAP compress high-dimensional data — with a worked PCA example and interview traps.

Case Study: Ad Click-Through Rate Prediction (Meta / Google Ads-style)

Model interview answer for ad click-through rate prediction: why calibrated pCTR drives the auction, delayed labels and negative downsampling, sparse ID features, LR-to-DLRM model evolution, calibration monitoring, online learning and a low-latency serving architecture.

Bias–Variance Trade-off & Cross-Validation

Master the bias-variance decomposition, learning and validation curves, k-fold, stratified, group and time-series cross-validation, nested CV for honest tuning, and the data-leakage traps that make validation scores lie.

Regularization: L1, L2 and Elastic Net

Learn how Ridge (L2), Lasso (L1) and Elastic Net penalties shrink or zero out coefficients, why lasso does feature selection and ridge does not, how to pick lambda, and how the same idea shows up in logistic regression, neural nets and gradient boosting.

Model Training & Experimentation at Scale

Learn how to answer the training half of an ML system design interview: baselines, model family choice, temporal offline evaluation, tuning budgets, experiment tracking, distributed training, GPU cost estimation, embedding tables, retraining cadence, and off-policy evaluation.

Model Evaluation Metrics

Master the confusion matrix and its derived metrics, ROC vs precision-recall curves, log loss, calibration and ECE, cost-based threshold selection, regression and ranking metrics like NDCG, multiclass averaging, and how to tell real metric gains from noise.

ML Monitoring, Drift & Retraining

Learn why deployed models decay, how to monitor them in layers from system health to business KPIs, compute PSI and other drift statistics with worked numbers, handle delayed labels, and design retraining triggers with safe validation gates and rollback.

ML Data Pipelines & Feature Stores

Design the data side of an ML system: logging for train/serve parity, labelling strategies, point-in-time joins, negative sampling, batch vs streaming features, feature stores, training–serving skew, data validation, lineage and a worked notification-click pipeline.

Case Study: Search Ranking (Airbnb / E-commerce Marketplace Search)

Model interview answer for marketplace search ranking: two-sided objectives, retrieval vs learned ranking, position-bias-corrected labels, LambdaMART vs neural rankers, NDCG worked example, cold start, diversity re-ranking, serving architecture and monitoring.

Multimodal LLMs and Vision

Learn how multimodal LLMs actually process images: patch tokenization, vision-encoder pretraining, and how the model distinguishes between multiple objects in a scene through attention rather than bounding-box regression. Covers the practical gap between vision-language models and classical object detectors, common failure modes (counting, fine-grained discrimination, spatial relations), and prompting techniques (referring expressions, crops, set-of-mark) that make multi-object questions reliable in production.

Feature Engineering

Learn the feature engineering toolkit data scientists are tested on: scaling and transforms per model family, categorical encodings including leakage-safe target encoding, missing-value strategies, cyclical time features, point-in-time aggregations, feature selection, and sklearn pipelines that prevent training/serving skew.

Case Study: Real-Time Payment Fraud Detection (Stripe / PayPal-style)

Model interview answer for real-time payment fraud detection: sub-100 ms decisions, 0.1 % positives with asymmetric costs, delayed chargeback labels, point-in-time features and velocity counters, GBDT plus graph signals, PR-AUC and dollar-weighted evaluation, cost-based decision policy and a streaming serving architecture.