What 𝗠𝗟 𝗰𝗼𝗻𝗰𝗲𝗽𝘁𝘀 are commonly asked in 𝗱𝗮𝘁𝗮 𝘀𝗰𝗶𝗲𝗻𝗰𝗲 𝗶𝗻𝘁𝗲𝗿𝘃𝗶𝗲𝘄𝘀?

What 𝗠𝗟 𝗰𝗼𝗻𝗰𝗲𝗽𝘁𝘀 are commonly asked in 𝗱𝗮𝘁𝗮 𝘀𝗰𝗶𝗲𝗻𝗰𝗲 𝗶𝗻𝘁𝗲𝗿𝘃𝗶𝗲𝘄𝘀?

These are fair game in interviews at 𝘀𝘁𝗮𝗿𝘁𝘂𝗽𝘀, 𝗰𝗼𝗻𝘀𝘂𝗹𝘁𝗶𝗻𝗴 & 𝗹𝗮𝗿𝗴𝗲 𝘁𝗲𝗰𝗵.

𝗙𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹𝘀

– Supervised vs. Unsupervised Learning

– Overfitting and Underfitting

– Cross-validation

– Bias-Variance Tradeoff

– Accuracy vs Interpretability

– Accuracy vs Latency

𝗠𝗟 𝗔𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀

– Logistic Regression

– Decision Trees

– Random Forest

– Support Vector Machines

– K-Nearest Neighbors

– Naive Bayes

– Linear Regression

– Ridge and Lasso Regression

– K-Means Clustering

– Hierarchical Clustering

– PCA

𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 𝗦𝘁𝗲𝗽𝘀

– EDA

– Data Cleaning (e.g. missing value imputation)

– Data Preprocessing (e.g. scaling)

– Feature Engineering (e.g. aggregation)

– Feature Selection (e.g. variable importance)

– Model Training (e.g. gradient descent)

– Model Evaluation (e.g. AUC vs Accuracy)

– Model Productionization

𝗛𝘆𝗽𝗲𝗿𝗽𝗮𝗿𝗮𝗺𝗲𝘁𝗲𝗿 𝗧𝘂𝗻𝗶𝗻𝗴

– Grid Search

– Random Search

– Bayesian Optimization

𝗠𝗟 𝗖𝗮𝘀𝗲𝘀

– [Capital One] Detect credit card fraudsters

– [Amazon] Forecast monthly sales

– [Airbnb] Estimate lifetime value of a guest

Like if you need similar content 😄👍