RevSure Marketing Mix AI Engine Overview

RevSure Marketing Mix Modeling Introduction

RevSure’s marketing mix modelling (MMX) solution helps CMOs and their marketing teams make better planning and spend allocation decisions across different channels and investments such as Dark Social (Podcasts, etc.), Brand, Paid Ads (Google, LinkedIn, Meta, Bing), Events, Sales investments, Organic Search, Content and OOH.

MMX uses a multi-variate AI-based regression engine that quantifies the contribution and ROI of each channel towards pipeline and bookings for every quarter in the past and on a rolling basis. It can account for the impact of macro-economic factors as well as competitive events and actions.

It further provides the ability for marketing teams to integrate and quantify the impact of dark social and brand awareness metrics on overall long-term and short-term pipeline and bookings performance.

MMX insights enable customers to determine the most effective allocation of their marketing budget across channels for the upcoming quarters.

Algorithmic Methods

RevSure’s MMX quantifies the contribution to pipeline and booking based on GTM, marketing and non-marketing factors.
These factors are a group of features/variables from the input data (including online and offline channel spends) and can be defined and configured from the RevSure UI.
We use a multivariate AI-based regression engine trained on historical data using these factors for forecasting various metrics.
These models get trained for each customer separately and adapt to the customer’s data and GTM motion. The variables and features considered can be adapted for each customer.
Through these models and analytical techniques, we extract insights about the impact of each factor on predictions. This helps us understand what factors influence the outcomes and to what degree.
For instance, the model allows us to dissect the contribution of individual factors, such as LinkedIn impressions or ad spends, on the forecasted results, which helps the business identify the key drivers of performance.
We build individual models for various metrics such as ‘pipeline generation volume’, ‘pipeline generation value’, ‘booking generation volume’, and ‘booking generation value’. For each of these metrics, we provide a baseline and the contribution of each of the factors.

Feature List

A few examples of GTM variables and features we use (based on available data).

Factor Group	Features
LinkedIn	LinkedIn spend LinkedIn impressions LinkedIn engagements # LinkedIn campaigns Audience size Audience profile
Google	Google spend Google impressions Google engagements # Google campaigns Audience size Audience profile
Facebook	Facebook Spend Facebook Impressions Facebook Engagements # Facebook campaigns Audience size Audience profile
Events	Event spend #Events # Audience/Campaign member size and profile
Organic Social	Organic Social posts Organic Social impressions Organic Social engagement (clicks, follows, shares, reactions, comments)
Brand (optional)	# Brand impressions (across channels) # Brand campaigns $ Brand spend #Brand Awareness metrics (as available)
Sales and BDR	# Sales Reps $Sales Spend #Sales campaigns #BDRs $BDR spend # BDR campaigns
Other Marketing	Content, Email Marketing, Content Syndication, Webinars (can also be quantified separately as required)
Dark Social & Other	# Other campaign spends and activities across OOH and Podcasts # Podcasts, Podcast Impressions, #Podcast views
Macroeconomic	US Real GDP Growth Rate US Federal Funds Rate US Unemployment Rate

Key Output Metrics

Generated Pipeline Volume and Value
Generated Booking Volume and Value
Pipeline Contribution
Booking Contribution
Pipeline ROI
Booking ROI