CS team finding out an account is at risk when they send a cancellation request rather than 60 days earlier when outreach could have changed the outcome?
Health scores in your current CS tool that CSMs don't trust because they don't reflect the signals that actually matter for your product?
Customer Health Scoring Software
Custom customer health scoring platforms that aggregate product usage, support history, engagement, and billing signals into a single score for each account -- surfacing at-risk accounts weeks before churn signals are obvious, and identifying expansion candidates before they go to a competitor.
A health score is only useful if it reflects what actually predicts churn in your customer base. We build health scoring engines tuned to your product signals, your customer segments, and your historical churn patterns -- not a generic template from an off-the-shelf CS tool.
Multi-signal health score engine aggregating usage, support, NPS, billing, and engagement data
Configurable signal weighting tuned to what actually predicts churn in your customer base
At-risk account alerting and escalation routing before churn signals are obvious
Health score trend tracking showing whether accounts are improving or deteriorating over time
RaftLabs builds custom customer health scoring platforms that aggregate product usage, support history, NPS and CSAT responses, billing signals, and communication cadence into a single account health score. Health scores surface at-risk accounts weeks before churn signals become obvious and identify expansion candidates before they go quiet. Most health scoring projects deliver in 10 to 14 weeks at a fixed cost.
100+Products shipped
·24+Industries served
·FixedCost delivery
·10-16Week delivery cycles
Health scores that don't reflect reality don't get used
The most common failure mode in customer health scoring is a score built on the wrong signals, or on the right signals with the wrong weights. A CS platform's out-of-the-box health score treats all customers the same. It doesn't know that your power users log in three times a week but your at-risk accounts log in once, or that a spike in support tickets for one customer segment is a leading indicator of churn while for another segment it's a sign of active adoption.
We build health scoring engines on top of your actual data. During discovery, we analyze which signals correlate with churn versus expansion in your customer base. We build a data pipeline that aggregates those signals from your product, your support system, your CRM, and your billing platform. The resulting score reflects your customer reality -- which is why CSMs use it to make decisions rather than ignoring it.
What we build
Multi-signal health score engine
A scoring engine that combines product usage, support history, survey responses, CRM activity, billing signals, and communication cadence into a single account health score. Signal weighting is configurable and can be adjusted as you learn more about which inputs are most predictive for your customer base. Scores are recalculated on a defined cadence -- daily for most implementations -- so CS teams are always working from current data rather than a weekly export. Score methodology is transparent to CSMs so they understand why an account is red rather than just seeing a number.
Product usage data integration
Integration with your product's analytics layer to pull session frequency, feature adoption, depth of use, and recency signals into the health score engine. Works with Segment, Mixpanel, Amplitude, Heap, and custom event tracking implementations. User-level and account-level usage rolled up to the account health view. Usage trend data so CSMs see whether engagement is stable, growing, or declining -- not just a point-in-time number. The usage integration is the most predictive input for most SaaS products, and we prioritize getting it right before adding secondary signals.
Support and CSAT signal aggregation
Support ticket volume, resolution time, escalation rate, and ticket sentiment pulled from Zendesk, Intercom, Freshdesk, or your support system. CSAT and NPS survey responses integrated from Delighted, Medallia, or your survey tooling. Support signals weighted based on severity -- an escalation in the last 30 days carries more weight than a closed low-priority ticket from six months ago. Sentiment analysis on ticket content to identify accounts expressing frustration even when ticket volume is low. Support and survey signals often surface churn risk two to four weeks before usage signals do.
Segment-level health analytics
Portfolio health views that aggregate account scores by CSM, segment, plan type, industry, or account size -- so managers can see which parts of the book of business need attention without reviewing individual accounts one by one. Cohort comparison showing how accounts onboarded in different periods are tracking against each other. Health distribution across the customer base -- what percentage is healthy, neutral, or at risk -- with trend over time. The segment view that turns individual account scores into a portfolio management tool.
At-risk account alerting and escalation
Configurable alert thresholds that trigger notifications when an account's health score drops below a defined level or when a specific signal changes sharply -- for example, usage dropping by 40% week-over-week or a detractor NPS response submitted. Alerts route to the account owner with context: which signals drove the change and what the recommended intervention is. Escalation routing for high-value at-risk accounts that require manager visibility. Alert fatigue is managed through threshold configuration so CSMs receive actionable signals, not noise.
Health score trend tracking
Historical health score tracking for every account so CSMs can see whether an account has been declining for two weeks or two months -- and whether previous interventions moved the score. Score trajectory visualizations alongside the signal data that drove each movement. Trend data for QBR preparation so customer conversations are grounded in evidence rather than recollection. Reporting for CS leadership showing which accounts were recovered from at-risk status and which continued to deteriorate despite intervention, feeding back into score methodology improvement.
Frequently asked questions
The strongest churn predictors for most SaaS products are declining product usage (especially a sharp drop in session frequency), support ticket escalations, missed QBRs, slow response to CS outreach, and payment delays or downgrade requests. Expansion predictors are typically the inverse -- growing usage depth, feature adoption of advanced capabilities, positive NPS and CSAT, and proactive inbound questions about capabilities they aren't using yet. The specific weights depend on your product and customer base. We analyze your historical churn data during discovery to identify which signals were present in accounts that churned 60 to 90 days before the cancellation, and weight the scoring model accordingly.
Signal weighting is part of the health score design process, not a default configuration. We start by mapping which signals are available for your accounts, then analyze correlation with churn events in your historical data. High-correlation signals get higher weights. Signals that are noisy or inconsistently populated get lower weights or are excluded until data quality improves. Weights are revisited after the first 60 to 90 days of live operation once we can compare predicted risk to actual outcomes. Most implementations use a weighted composite model with signal recency factored in -- a support escalation from last week matters more than one from six months ago.
A health score without a workflow attached to it is just a number. We build the connection between the score and the CS team's task management so that when an account drops into at-risk territory, a specific playbook is triggered -- whether that's a CSM outreach task, an executive business review scheduling prompt, or a manager escalation. Playbooks are configurable per segment, plan type, or account value so a high-value enterprise account at risk gets a different response than a small-business account. Health score changes appear in the CS team's daily workflow view rather than in a separate analytics tool they have to remember to check.
A customer health scoring platform -- signal aggregation from two to four sources, configurable scoring engine, account portfolio view, and at-risk alerting -- typically runs $15,000 to $50,000 and delivers in 10 to 14 weeks. Cost increases with the number of data source integrations and the complexity of the segment-level analytics. Adding CS team workflow and playbook automation to the scoring platform is a separate scope that typically adds $20,000 to $40,000. We scope and price every project before starting so you know what you're getting before committing. Fixed cost, no hourly billing.
Tell us what data sources you have, how many accounts your CS team manages, and what your current early warning system looks like. We will scope a scoring model that reflects your customer reality.
