Machine Learning With RAPIDS

NCA-ADS · 32 questions

• A courts and clerk e-filing analytics team needs a tabular permit-approval risk model trained quickly on GPU. Which approach best fits NVIDIA RAPIDS accelerated training for that task?
• A library program attendance analytics team will train an early-warning model on large school-district tabular features overnight. Which training choice best leverages GPU acceleration for that booster workload?
• A parks and recreation demand desk compares logistic regression fit time for the same feature matrix using cuML on GPU versus scikit-learn on CPU of the same host. What outcome should they expect when the GPU path is correctly used?
• A school-district enrollment analytics pipeline trains cuML models but repeatedly copies the same feature matrix between host RAM and GPU mid-fit. What change best improves training efficiency?
• A county assessor parcel desk needs similar-case retrieval so clerks can pull look-alike parcels during casework. Which GPU RAPIDS approach best fits that similarity task?
• A 311 resident-service analytics team must train separate district triage models overnight inside one maintenance window. What approach best uses GPU training throughput for that multi-model batch?
• A permitting and inspections bureau wants to predict EMS response minutes from station distance and traffic features. Which learning family should the team choose?
• A fire and EMS analytics desk must assign each 311 ticket to a discrete priority tier for triage. Which RAPIDS modeling choice matches that goal?
• A public hospital district throughput desk has neighborhood service-demand features but no pre-assigned segment labels. What technique should they use to group similar neighborhoods?
• An elections operations (non-partisan) data team’s SLA target is a binary pass/fail readiness flag for poll-site kits. Which supervised family should they pick?
• A municipal fleet telematics desk wants to discover route-similarity groups for solid-waste trucks without predefined route labels. How should clustering outputs be used?
• A solid-waste route optimization analytics team’s KPI is continuous fine amounts, not discrete violation categories. What modeling mistake should they avoid?
• A county social-services case analytics team must test whether a property-tax assistance model generalizes beyond the training period. What evaluation design is most honest?
• A city planning zoning analytics team wants to compare two cuML models fairly before promoting one. What evaluation practice should they follow?
• A city open-data portal sees near-perfect training accuracy, yet scores drop sharply when the model is applied to newly annexed districts. What does that pattern most clearly indicate?
• A county public-health analytics housing model shows high error on both training and validation in some runs, then wild swings across folds in others. How should the team describe the failure modes at associate depth?
• A transit authority ridership desk finds a complex model’s validation lift is tiny and not operationally meaningful versus a simpler cuML baseline. What should they prefer?
• A water-utility sensor analytics team is tuning GPU XGBoost for a transit-delay tabular model. Which hyperparameters are most directly meaningful to search first for tree boosters?
• An emergency-management fusion cell has a tight deadline to tune a RAPIDS model and cannot afford a full combinatorial grid. Which HPO strategy fits best?
• A housing-authority waitlist analytics team finished an HPO sweep and must reproduce the winning configuration next sprint. What practice links tuning to reproducibility?
• A courts and clerk e-filing analytics team is tuning trees for small-district datasets that overfit easily. How should they set the HPO search space?
• A library program attendance analytics team sees validation metrics plateau across many HPO trials with no civic-value gain. What should they do?
• A parks and recreation demand desk needs robust evaluation for a citywide classifier and has no natural chronological split. Which cross-validation approach is appropriate?
• A school-district enrollment analytics team has rare flood-complaint labels and must keep class mix stable across CV folds. What should they use?
• A county assessor parcel desk is forecasting weekly demand and worries shuffled k-fold will leak future weeks into training. Which CV design should they prefer?
• A 311 resident-service analytics team finished k-fold evaluation and must decide whether a RAPIDS model is ready for a pilot. What should they do with the fold metrics?
• A permitting and inspections bureau is comparing two RAPIDS estimators with cross-validation. How do they keep the comparison fair?
• A fire and EMS response-time analytics team reviews a confusion matrix for high-risk inspection predictions. Which reading best supports civic risk decisions?
• A public hospital district throughput desk finds that missing a bridge-access defect flag is far costlier than extra review alerts. Which metric priority fits that asymmetric cost?
• An elections operations (non-partisan) data team must explain precision versus recall tradeoffs to a non-technical department head reviewing a ballot-box logistics risk model. What should they emphasize?
• A municipal fleet telematics desk finds that both false alarms and missed high-priority 311 triage tickets hurt a pilot equally. Which metric should they optimize?
• A solid-waste route optimization analytics team sees 95% accuracy on tickets that are mostly low priority and wonders if the RAPIDS classifier is actually useful. What should they recognize?