Analytics

The Analytics module is your one-stop view of how the whole company is doing. Unlike module-specific dashboards (e.g. the Performance dashboard, the Engagement dashboard), Analytics is the cross-module composition layer: it brings together reports, rule-based insights and, when enabled, AI-generated narratives across People, Recruiting, Performance, Compensation, Time & Leave, Engagement, and Career.

Pages

The tab strip carries seven tabs: Overview, People, Performance, Recruiting, Surveys, Governance, Builder. The deeper dives keep their own pages and open from inside those tabs: DEI, Retention, Succession, and Pay Equity from the "More people analytics" cards on the People tab, and Insights Hub from the "View all insights" link on the Overview.

Analytics Home (/analytics)

Your daily landing page. Three rows:

• Your saved reports: cards for reports you've built or pinned, each showing the headline value, directional delta, and a 12-point sparkline.
• Featured insights this week: top 3 insights ranked by severity. Click any card for evidence + recommendations, or "View all insights" to open the Insights Hub.
• Modules at a glance: 7 module cards (People, Recruiting, Performance, Compensation, Time & Leave, Engagement, Career), each with 3 KPIs and a deep-link to the module's analytics page.

On Growth and above, open a saved report in Analytics > Builder and choose Set as Home to show it on Analytics Home. The preference is saved for your account; the report remains subject to its access permissions.

Insights Hub (/analytics/insights)

Reached from the "View all insights" link on Analytics Home. Triage view for cross-module alerts. Severity tabs (All / Critical / High / Medium / Low) with count badges, search across title/description/module, and per-card actions: Details (opens the evidence + recommendations modal) and Acknowledge (marks the insight as resolved).

Insights have two flavors:

• AI (✦ badge with confidence score): generated by Sparko's AI. AI-generated insight narratives are available on Growth and above by default; contact Sparko support about an exception.
• Rule (no badge): deterministic threshold queries (e.g. "PTO accrual >25 days"). Rule-based insights, their evidence and recommendations, dashboards, and standard reports remain available on Core.

AI insight narratives are generated weekly for Performance, People, Engagement, Recruiting and Skills, with a monthly Org Health narrative. They are available on Growth and above by default. Analytics pages, reports, dashboards and rule-based insights remain available according to their own permissions and plan features. Sparko manages plan exceptions. On-demand regeneration requires permission to generate insights, queues the existing job, and uses an AI action from the generation pool when enabled on Core.

Performance Analytics (/analytics/performance)

Cross-module performance signals: OKR Health funnel (on-track / at-risk / off-track / completed), calibration band distribution and the at-risk employees rail on every plan. On Growth and above you also see the department × performance-band matrix, which shows where your high performers sit, and the Cohort comparison tab (heatmap plus drill table). On Core those two show a locked card where an admin can upgrade and anyone else can request it.

People Analytics (/analytics/people)

Headcount metrics: department breakdown, headcount-by-leadership (CEO excluded), tenure buckets, locations, 12-month headcount trend, and a movement summary (hires / promotes / transfers / exits).

Recruiting Analytics (/analytics/recruiting)

Hiring funnel (applicants → phone screen → interview → offer → hired), hiring-plan progress per department, open requisitions table with days-open and stage, source-mix bars. Cost per hire is on Growth and above; on Core its tile reads "On the Growth plan" with an upgrade or request button below it.

DEI Analytics (/analytics/dei)

Reached from the "More people analytics" cards on People Analytics. Diversity, equity, and inclusion. Gender donut, ethnicity donut (gated by analytics.dei.view_pii), leadership representation by level, department × gender stacked bars, hire/promote/exit funnel by gender, pay-gap summary table. Cohort-row counts below 5 employees are suppressed under a k-anonymity floor.

Pay Equity (/analytics/pay-equity)

Reached from the "More people analytics" cards on People Analytics, or from the Compensation Hub. Controlled and uncontrolled pay-gap analysis across cohorts (band × department), plus outlier employees whose base salary is >15% off their cohort median.

EU transparency tab

Shown when you cover at least one paying entity in an EU country and hold both the pay equity view and the DEI personal data permissions. Pick the entity and the year on the right of the tabs.

• The table is the gender pay gap by category of worker: people, mean gap and median gap on hourly pay, and a flag. Positive means men are paid more. A category where the women or the men are fewer than the smallest group size shows Suppressed and Small group. Whole entity at the bottom is reported only.
• Flags. Below 5%, Close to 5% (4% or more) and Assess jointly (5% or more).
• Stats button shows the whole-entity mean and median gap, how many categories are at 5% or more, and the next required report date for the entity's size.
• Run report (pay transparency managers) recomputes the year's draft. Finalize report, under the table, freezes it and opens a 6-month remedy clock on each category at 5% or more.
• People left out. Anyone the report could not include is listed above the table by reason: pay that could not be read, no exchange rate, no pay in the year, no weekly hours, or no category of worker. To finalize anyway, tick the confirmation first.
• Payroll pay. When the entity ran Sparko payroll in the year, regular pay is annualised over the days the person's regular runs cover. Bonuses, settlements, manual items and off-cycle runs count as paid. Once any category is a small group, the table shows totals only, without the split into men and women.
• Decide a flag. Click an Assess jointly row on a final report. Pick Open, Justify (write the reasons), Remedy (write the plan) or Joint assessment, and an owner. The owner, or every pay transparency manager when there is none, is reminded 30 and 7 days before the remedy date and on the day.
• Requests and Postings in the header are counts. Requests opens the entity's open pay information requests, each linking to Compensation › Pay information. Postings lists the entity's job postings under an EU pay range law; one that cannot show a range has Use band range and Edit job, and a live one also has Pause.
• Export report downloads a PDF or CSV, either indicators only or the full report by category. Exports are marked as a management report, not filing-ready, until a national format is verified.

The gap report is on the Business plan. Pay information requests work on every plan.

Categories tab

Each role level is its own category of worker until HR groups levels of equal value. Tick two or more levels, name the category and say why they are equal in value, then Group. Ungroup takes a level back out. The list shows the levels with people in the selected entity; Show all levels shows the rest. Changes apply to the next report run and new replies.

Bias & Governance (/analytics/governance)

The adverse-impact report third-party auditors ask for, computed live rather than assembled from exports. Requires analytics.dei.view_pii.

Sparko runs the four-fifths (80%) rule across three decisions:

• Hiring: advancing past AI screening, the automated decision NYC Local Law 144 regulates. Grouped by candidates' own voluntary EEO answers.
• Promotion: recommended for promotion in a completed talent-calibration session. Considered = everyone reviewed; selected = recommended.
• Compensation: a merit increase approved. Considered = everyone whose recommendation was decided; selected = approved.

Each is broken out by gender, race/ethnicity, veteran status and disability status.

In the app, the method summary lives under Help & FAQ → Analytics & Fairness.

The group-first view is the one an export-based tool cannot produce: it shows where a single group is disadvantaged at more than one stage, which is the pattern that matters and the one a per-decision report hides.

Only finished decisions count. A calibration session still in discussion, or a merit recommendation nobody has decided yet, is left out: grading work in progress invents findings.

Small groups are withheld. Under 5 people, the group's numbers are hidden entirely rather than shown; between 5 and 30 they are shown but marked provisional. A withheld group's size cannot be recovered by subtracting the groups that are shown.

When it can't be computed, it says so rather than showing a clean result. If demographic values cannot be read, the report is marked incomplete: on screen and in the export. "Not enough data to audit yet" is never presented as "no bias found".

CSV export for filings under NYC LL144, Illinois HB 3773 and Colorado SB 24-205, carrying the window and a data-quality column alongside each row.

This is a diagnostic, not a determination. Consult qualified counsel before acting on it.

Retention (/analytics/turnover)

Reached from the "More people analytics" cards on People Analytics. The page is one table of people who may leave next, with the views on tabs.

The header has a Period picker, a stats button (Show summary stats / Hide summary stats) and Run report, which opens the Report Builder. The tabs row reads High, Medium, Watch, Insufficient data, Trends, Exit themes. Each band tab carries a count of the people in it, counted the way the Engagement risk mix counts them: everyone employed, new joiners and people on leave included, once each at their latest score, as long as that score falls inside the Period. The band tabs need a plan that includes flight risk; without one, only Trends and Exit themes show. On a band tab the row also has Filter (Team, Top factor, Action taken) and a search box (Search people, teams, factors).

• Band tabs. One table per band with the columns Person, Team, Risk (100 minus retention score) with the band, Change since the last score, Top factor and Act. Scores come from the Engagement module, which shows the retention score itself (lower means more at risk); Risk is the same number turned round so that higher means more at risk, so a retention score of 18 reads as risk 82. Rows page 12 at a time. The table lists at most the 200 highest in a band and says when it is capped.
• Act. On High and Medium rows, Act (or a click on the row) opens the panel described below. Once something has been done, the cell shows what, such as "1:1 scheduled", "Pay change sent" or "Review open", so two people don't act twice. Watch rows have no Act.
• Insufficient data. A score is built from six areas: engagement, performance, recognition, growth, time off and tenure. An area counts only when Sparko has real data for it. Someone with real data in fewer than three areas is listed here, not in a risk band, with no score and no Act. The Data column says how many areas were judged. Only finished reviews and OKRs that are completed or past their end date count toward performance, so drafts and goals still in progress never count as misses. In someone's first 90 days, recognition and growth are not judged, and performance counts reviews only.
• Stats. The stats button reveals attrition, voluntary exits, top exit reason and the high-risk count, then Retention by tenure (0–6m / 6m–1y / 1–2y / 2–4y / 4y+) and Model accuracy. How it is measured opens the accuracy drawer.
• Trends. The attrition trend line, exit reasons from exit interviews, and a department × month heatmap of attrition counts.
• Exit themes. Opens from the tab, or from the link #exit-themes.

Exit themes generate in the background. The page tells you when they are ready. Themes are written from scrubbed exit-interview answers, and no individual answer is ever shown. Each theme carries its share of exits, the departments that show it and a recommendation. A row opens a drawer with the full detail. A theme appears only when it covers five or more exits, and a department's count appears only when that department contributed five or more, so it needs at least five completed exit interviews in one department before anything is shown. It is regenerated at most once every 15 minutes. It is Business and Custom (the rest of the page is Growth).

Model accuracy sits in the stats, because an accuracy figure on another page is one nobody checks before acting on a name. It shows lift, precision, recall and base rate. The How accurate is this? drawer grades past risk levels against who actually left:

• A calibration table: for each risk band, how many people were in it and what share of them left within the horizon. A band's rate is readable at small numbers where a single headline percentage would mislead.
• Only finished horizons count. Scoring someone as "correctly predicted to stay" a week after the prediction is how this number gets inflated, so predictions still inside their window are excluded rather than counted as successes.
• One person, one observation, even though scoring runs weekly.
• Departures the model doesn't claim to predict leave the group: a recorded layoff, retirement or end of contract is a different process, not a flight-risk miss. These notes sit under Details in the drawer.
• Bands under 5 people are withheld, and the derived figures are withheld with them so the hidden counts can't be recovered.

Until a group of predictions has finished its horizon, the page says "Still accumulating" and the drawer names the date the first readout becomes available. It does not show a number derived from an unfinished cohort.

Departures with no recorded separation type are counted, and the drawer tells you how many: recording voluntary or involuntary at offboarding sharpens the figure over time.

Acting on a flight-risk flag

Where to find it: the Act button on each row of the High and Medium tabs on Retention. Act is part of the Business plan.

Act opens a panel on the right:

• Why they were flagged: the risk score (100 minus the retention score) and up to three reasons. HR with company-wide engagement access also sees the evidence behind each reason and a two-to-three sentence summary of what is driving the score. Sparko writes the summary within a few minutes of a new High or Medium score, not on a weekly schedule. A new score with the same band and the same reasons keeps the summary it had. If the summary is not there yet, the reasons above are the same facts it is written from.
• One choice: pick one action. You can confirm one action per flag.
  • Propose a retention pay change. You type the increase as a percentage. Sparko never suggests a figure. The change goes into the normal approval chain.
  • Schedule a 1:1 with their manager at a time you pick. The manager gets a notification, unless you are the manager. Nothing on the meeting mentions the flag.
• What will happen: one line before you confirm, such as who approves the pay change first or when the meeting is.
• The record: the score is saved with your action, so Retention can show later whether acting on a flag kept people.

If you manage the person, your own approval step is skipped and the pay change goes to the next approver above you. If nobody is above you in the chain, it goes to an HR admin.

If an option can't run, the panel says why. For example, a pay change may already be waiting for approval, or the person may have no manager on record.

Each row shows what has already been done, so two people don't act twice. Your own flag is never on your list.

Succession (/analytics/succession)

Reached from the "More people analytics" cards on People Analytics. A role card per career-path level, sourced from the Career module's framework data.

Each card shows the incumbents, a risk read (Stable / Flight risk / Retirement risk), and the named successors on that role's bench. Every successor carries a readiness pill (Ready now, Ready in 1–2y, Developing, or Long-term), computed from how much of the target level's required competencies and skills they already meet, plus a count of the requirements still open.

Above the grid: four tiles (critical roles, average bench depth, ready-now successors, roles flagged at risk), a By role / By incumbent / By bench depth view switch, a search box, and department + risk-level filters.

Add successor on a card (or Identify successor in the header) names someone for that role as a Primary or Aspirational nomination; the same nomination shows up on their profile's Career tab under Target roles. Export plan downloads the visible roles as CSV. Naming successors and setting the risk level require the Manage Succession Plans permission: everyone else sees the plan read-only.

Survey Trends (/analytics/surveys)

Cross-survey participation and status board: counts by status, participation-over-time bars, and eNPS per survey. Rows link to each survey's full results in Engagement (Engagement > Surveys > View results). Survey creation and per-survey results live in the Engagement module.

Report Builder (/analytics/builder)

Build custom reports or start from a template. 3-pane workspace:

• Library rail (left): Reference reports (7 Analytics pages as one-click composites), Templates (16 atomic charts by module), My reports (your saved ones), Recent.
• Center canvas: Editable report name, action row (Set as Home / Save / Share / Schedule / Export / Run), tab strip (Data / Filters / Visualization / Preview), and the live chart preview.
• Right rail: Chart-type picker (Bar / Line / Pie / Donut / Distribution / Heatmap / Table: distribution + heatmap arrive in a follow-up release), data source dropdown, X-axis and Y-axis field slots, and the available-fields list.

Click a field to assign it to X or Y axis. Click Run to execute the query against the live database and render the result.

To download a saved report, open More > Export report, pick CSV or PDF and click Export. Sparko prepares the file in the background while the dialog waits, then shows a Download button. The file is named after the report and the day you asked for it, for example headcount-by-department-2026-10-27.csv. If it takes longer than a minute, click Keep waiting, or close the dialog and reopen it later to pick up the same export.

Known Limitations

• Export formats: CSV and PDF only. The PDF is a table of the report's data and does not include the chart.
• Period windows differ by measure. Changing a period refreshes the relevant request: People movement follows the selected window, while headcount distributions describe current employees and the headcount trend and boomerang count retain their 12-month windows. Performance uses the chosen quarter or review cycle for the corresponding view; Retention uses its selected period. A period change does not make every metric historical.
• Turnover and Performance Analytics stat tiles: a few individual tiles on these two pages (e.g. specific attrition and OKR-progress percentages) are still showing placeholder figures rather than your company's live numbers: everything else on the page is live. This is being fixed.
• AI insight generation runs weekly for Performance, People, Engagement, Recruiting and Skills. The Org Health narrative is monthly. Compensation and Time & Leave are not covered. These generated narratives are available on Growth and above by default; contact Sparko support about an exception. This does not change access to standard reports, dashboards or rule-based insights.
• Scheduled report delivery via Slack or a shareable link silently falls back to in-app delivery only: if you pick Slack as the delivery method in Schedule Report, no Slack message is actually sent.
• Visit Insights Hub to see new AI insights; there is no push notification.

Permissions

Action	Permission
See the Analytics nav entry	analytics.module.view (HR Admin / IT Admin / Manager / Super Admin)
View DEI Analytics page	analytics.dei.view (HR Admin / IT Admin)
See ethnicity + pay-gap inside DEI	analytics.dei.view_pii (HR Admin only)
Build / edit custom reports	analytics.reports.create (HR Admin / IT Admin)
Schedule recurring delivery	analytics.reports.schedule (HR Admin / IT Admin)
Share saved reports	analytics.reports.share (HR Admin / IT Admin)
Acknowledge insights	performance.insights.acknowledge (HR Admin / Manager)

Employees do not see the Analytics nav entry at all. Analytics is the whole-company view by design: managers with the analytics permission see company-wide aggregates, not a subtree slice. People Analytics is open to HR and managers alike; the deeper breakdowns (DEI, Retention, Pay Equity) additionally require company-wide permissions and show restricted or empty states without them.

Tier availability

See docs/FEATURES_AND_PRICING.md § "6. Reporting & Analytics" for the per-tier feature matrix.

Related

• AI Features Overview