Data & Analytics

Custom ranking metric combining normalized weighted Gini coefficient with top-K% capture rate for imbalanced classification with class-weighted evaluation

Aggregate panel/sequential data with type-appropriate statistics — numeric (mean/std/min/max/last) and categorical (count/last/nunique) — then concat into flat features

Fit unsupervised transforms (scaler, PCA, variance filter) on combined train+test data for more stable statistics, especially on small datasets

Parallel-load per-subject parquet time-series files with ThreadPoolExecutor and flatten describe() statistics into tabular feature vectors

Builds user-level features by accumulating statistics across sequential event sessions before each assessment point.

Reshapes tabular features into 2D pseudo-images via random feature permutation, enabling CNN-based feature interaction learning.

Wrap PyTorch TabNet in a scikit-learn BaseEstimator with built-in imputation and early stopping for use in VotingRegressor ensembles

Compute min/max/mean/std of Euclidean distances from all entities to a key point, then aggregate per group for spatial feature engineering

Map calendar dates to categorical season phases (offseason, preseason, regular, postseason) using np.select with boundary date conditions

Engineers row-wise statistical features (sum, mean, std, skew, kurtosis, median, min, max) across all numeric columns per sample.

Use QuadraticDiscriminantAnalysis with regularization for binary classification on data with Gaussian cluster structure

Computes all numeric RDKit molecular descriptors from SMILES strings, filtering out NaN, constant, and infinite values to produce a clean feature matrix.

Augments training data with high-confidence test predictions as pseudo labels, retrains the model, and keeps the result only if OOF AUC improves. A semi-supervised technique for tabular competitions.

Rebalances training data by oversampling the majority class to match a known test-set class prior, reducing prediction miscalibration.

Mirror spatial coordinates and angles so all plays face the same direction — removes left/right asymmetry from sports and spatial data

Parse structured text fields like '1 RB, 2 TE, 2 WR' into separate numeric columns per category

Trains separate models for each discrete category (e.g., molecule type, product class) to capture type-specific patterns.

Apply VarianceThreshold within each data partition on combined train+test to select informative features per subgroup

Uses negative row-wise Pearson correlation as a differentiable loss function for multi-output regression, directly optimizing the competition metric.

Uses Optuna with TPE sampler for Bayesian hyperparameter optimization of LightGBM, searching key params like num_leaves, depth, and learning rate.

Scores features by comparing actual importances against a null distribution from shuffled targets, removing features that cannot beat random noise.

Converts molecular SMILES strings to fixed-length Morgan fingerprint bit vectors using RDKit for use as tabular ML features.

Applies logit transformation to base model probabilities before fitting a logistic regression meta-learner, enabling principled linear combination in log-odds space.

Iterates through rows chronologically to accumulate user statistics, fetching current state before updating to prevent future data leakage.