You’re asked to predict contract renewal for enterprise customers of a video-conferencing product after a spike in call disconnects. Design a modeling approach: define the label (renewal within the next contract period) and prediction horizon; specify features such as disconnection rate per 1k minutes, percent of meetings affected, time-to-resolution, SLA breaches, support ticket volume, NPS/CSAT, active seats, usage intensity, industry, account tenure, and price/discounts; discuss when logistic regression is preferable to gradient-boosted trees or deep models (interpretability, small-N, linear signal, sparse features, latency constraints) and when complex models are justified; prevent leakage (e.g., features created post-renewal), address class imbalance, consider survival analysis vs binary classification for censored data, and optionally add monotonic constraints; outline evaluation beyond AUROC (PR-AUC for rare churn, calibration curves/Brier score, cohort- and time-split backtests, stability under distribution shift), and compare rank-based vs calibrated thresholding; translate scores into actions with cost–benefit thresholds, expected ROI, and capacity constraints; provide a minimal viable feature set and justify it.