Research topic
Marketing automation
Deciding whether, when and where to send a message, within fatigue limits, time zones and consent.
Each paper states its method, puts its evidence in captioned tables and ends with its limitations.
Papers
Marketing automation as a constrained decision system: an event-driven design
We describe a design that treats each marketing send as a decision: event intake, causal effect estimation and policies bound by explicit constraints.
Consent-aware marketing automation: purpose and consent as inputs to every decision
We describe a design that makes consent and purpose inputs to data access, feature computation, model training and sending, not a flag checked at send time.
Send-time selection across time zones: a constrained, experimental design
We describe a design that picks a send window per customer and message from local routines, under quiet hours and contact limits, and learns by randomising.
Messaging fatigue and suppression: a design for deciding when not to send
We describe a design that estimates the net value of one more message per customer, counting lost subscribers, and suppresses sends whose value is negative.
Lifecycle state machines for customer automation: explicit states with inferred transitions
We describe a design that places each customer in one lifecycle state, infers transitions from events, and passes the state to automated decisions.
Goal-driven marketing agents under explicit constraints: a design
We describe a design for marketing agents that choose budgets, channels and messages toward long-term value, within hard constraints and human review.
Decision orchestration for marketing automation: whether, when and where to send
We describe a decision engine that chooses, per customer, whether to send a message, on which channel and when, from its estimated incremental effect.