Student Retention
Advisor Intervention Queue
Produces a deterministic intervention queue that prioritizes students requiring advisor outreach based on risk severity, intervention readiness, and timing sensitivity. The app converts broad risk diagnostics into daily and weekly action lists so frontline advising teams can allocate finite capacity to the highest-impact cases first.
The workflow layer integrates risk score, attendance trend, holds status, contactability, and prior intervention history to classify each student into urgency tiers and recommended playbooks. This structure reduces queue volatility and improves consistency across advisor teams by enforcing stable prioritization logic grounded in fixed seed data.
Outputs include intervention tier, next-best action, due date urgency, and expected persistence lift. Teams use the app for shift planning, advisor huddles, and escalation management where deterministic queue order and transparent rationale are required for accountability.
Attendance Outcome Analyzer
Quantifies the relationship between attendance behavior and persistence outcomes at course, section, and cohort levels. The app is built for early-alert and faculty success workflows where stakeholders need defensible evidence on attendance thresholds associated with retention deterioration.
The analysis layer links attendance bands to pass rates, credit completion, probation incidence, and next-term enrollment. It supports deterministic comparisons across modalities, course levels, and gateway classes, helping teams identify where attendance interventions can deliver the largest persistence lift.
Outputs include attendance threshold diagnostics, outcome gradients, and scenario-ready benchmark values. The app supports policy design, communication with faculty councils, and intervention timing decisions with reproducible statistics sourced from fixed seed data.
Cohort Risk Explorer
Maps persistence risk concentration across cohort definitions such as entry term, major family, aid status, residency, modality, and demographic segments. The app enables users to interrogate where risk clusters are deepest and whether those clusters are growing, stabilizing, or shrinking across terms.
The exploration layer supports comparative cohort slicing with deterministic counts, rates, and lift metrics. Users can move from institution-level views to narrow subcohorts while preserving fixed baseline definitions, ensuring analysis remains reproducible and comparable over time.
Outputs include ranked cohort risk concentration, delta versus institutional baseline, and severity banding. The app is used for targeting policy actions, allocating support budgets, and prioritizing cross-functional initiatives with clear evidence of where the largest persistence gains can be achieved.
Persistence Driver Diagnostics
Diagnoses which academic, behavioral, and financial factors most strongly influence term persistence for specific cohorts. The app provides a deterministic diagnostic environment where users can isolate driver effects by subgroup and compare relative contribution of attendance, credit completion, GPA trajectory, aid completeness, and advising engagement.
The analysis layer combines ranked driver impacts with subgroup variance panels so teams can detect where one factor dominates risk in one college while another factor drives outcomes in a different cohort. This supports interventions tailored to root causes rather than one-size-fits-all campaigns.
Outputs include deterministic impact rankings, normalized effect scoring, and confidence flags derived from fixed seed values. The app is used for strategy design sessions, advising model tuning, and persistence initiative postmortems where reproducibility and transparent logic are required.
Student Retention Hub
Provides a deterministic retention command center for academic leadership and student success teams. The hub combines cohort-level persistence snapshots, term-over-term trend tracking, and driver-pressure diagnostics so users can understand whether retention is on plan, where the largest risk is concentrated, and which intervention playbooks should receive attention first.
The app supports filtering by college, modality, aid status, and priority tier. It recalculates KPI cards, trend trajectories, diagnostic pressure views, and ranked focus segments from fixed seed data plus any workbook rows returned by the host. This makes the dashboard suitable for executive reviews, advising standups, and intervention planning where reproducible outputs are required.
The app is read-oriented and uses a managed Boardflare table to hydrate deterministic seed cohorts before the workbook row set is available. It is designed to remain stable in preview mode while still reflecting host-driven updates when the table sync changes.
Support Program Tracker
Tracks student support programs such as tutoring, emergency aid, peer mentoring, learning communities, first-year seminars, and advising navigation against persistence and completion goals. The app gives program owners a deterministic way to monitor participation, dosage, completion rates, retention lift, and budget efficiency within and across programs.
The monitoring layer compares actual lift against target lift, surfaces implementation variance by site and term, and highlights where dosage or completion rates are insufficient to produce expected retention gains. Users can filter by program type, site, term, and status to isolate the highest-pressure programs before monthly review meetings.
Outputs include program health status, lift-to-target gaps, participant mix diagnostics, and deterministic recommendations on scale-up, redesign, or resource reallocation. The app is intended for monthly program reviews and annual planning cycles where reproducible evidence is mandatory.
Term Variance Monitor
Tracks variance between retention plan and observed outcomes across terms, colleges, and cohort bands. The app is tailored for teams that must quickly identify where attainment is drifting before census and registration deadlines, then quantify whether variance is narrow and temporary or broad and compounding.
The core view pairs variance waterfalls with attainment heatmaps to reveal where absolute headcount gaps, rate deviations, and momentum shifts are most severe. Users can compare current term trajectory to prior term baselines and detect emerging risk in cohorts that are still above threshold but deteriorating quickly.
Deterministic outputs include variance class, gap size, and priority flags by organizational slice. These outputs support weekly corrective action forums and monthly planning reviews where consistent, reproducible interpretation is required across stakeholders.