Understanding what an actor wants at the motivation level — security, belonging, esteem, or self-actualisation — is more predictive of behavior than understanding what they say they want. The motivation hierarchy engine makes this computable from behavioral signals.
The Engines
- Tier Mapping — Five tiers adapted from Maslow: security (T1), belonging (T2), recognition (T3), achievement (T4), purpose (T5). Each tier has a set of behavioral indicators.
- Dominant Motivation Score — The tier with the highest evidence-weighted score is the dominant motivation. The score is a probability distribution across tiers, not a single label.
- Motivation Shift Detection — Detects when an actor transitions between dominant tiers. A sales prospect moving from T3 (recognition) to T1 (security) in week 3 of a deal is a strong signal of risk entering the process.
Code Walkthrough
// Score motivation tier distribution
function scoreMotivationHierarchy(signals) {
const tierScores = {
security: scoreTier(signals, SECURITY_INDICATORS),
belonging: scoreTier(signals, BELONGING_INDICATORS),
recognition: scoreTier(signals, RECOGNITION_INDICATORS),
achievement: scoreTier(signals, ACHIEVEMENT_INDICATORS),
purpose: scoreTier(signals, PURPOSE_INDICATORS),
};
const dominant = Object.entries(tierScores)
.sort(([, a], [, b]) => b - a)[0][0];
return {
distribution: tierScores,
dominant,
label: `${dominant}-motivation-indicators-present`,
};
}
What to Watch For
- Never collapse the tier distribution to a single label in high-stakes contexts. The full distribution carries more information.
- Motivation tier data is highly sensitive. Treat it as special category data under GDPR and restrict access to the minimum necessary personnel.