User Intent Prediction for Ads

What if you could predict which users are actually valuable before they convert? Most performance marketing strategies focus on what’s already happened - who clicked, who converted, and how much they spent. But what if you could optimise campaigns based on what will happen? Well that’s exactly what propensity models enable. By analysing user behaviour and intent signals, we can predict the likelihood of a conversion - allowing brands to make smarter, faster decisions across paid search and social. Understanding what a Propensity Model is A propensity model is a machine learning approach that predicts how likely a user is to take a specific action - whether it’s making a purchase, signing up, or returning to your site. Instead of treating all users the same, it helps advertisers: ✅ Identify high-value users before they convert ✅ Adjust bids dynamically based on predicted value ✅ Prioritise ad spend toward users who are more likely to convert Why Does This Matter? Ad platforms like Google and Meta rely on past conversion data. But for brands with long purchase cycles, waiting weeks or months for that actual revenue to come in isn’t practical. With propensity modelling, we estimate conversion value earlier and feed that data directly into bidding algorithms—enabling real-time optimisation. How It Works: 1️⃣ Data Collection – Analyse behavioural signals (session length, page views, interactions, historical purchases, etc). 2️⃣ Model Training – Machine learning identifies patterns that indicate conversion likelihood. 3️⃣ Real-Time Scoring – Every user gets a propensity score, predicting their likelihood to convert. 4️⃣ Activation in Paid Media – These scores are pushed to ad platforms, dynamically adjusting bids based on predicted value. Some results: Over the past 12 months, some brands using propensity models that we have built have seen ROI increase by 40% and conversion volume grow by 150% - driving significantly higher revenue at improved efficiency. But propensity modelling isn’t just for performance marketing. Its insights can help predict total future customer value and inform CRM, communication strategies, financial modelling, and beyond. Behavioural Insights The screenshot below is an example of a behavioural importance analysis, showing which user actions influence future value most. How to interpret the plots: - Each point represents a user record. - X-axis (SHAP Value): Left = lower probability of conversion, Right = higher probability. - Colour Scale: Blue = lower impact, Red = higher impact. Key takeaways - Propensity models provide a critical data point for understanding future customer value. - Integrating these signals into ad platforms can give brands a major advantage in bidding. - Their applications extend beyond performance marketing—impacting CRM, financial modelling, and overall business strategy.

I've watched 100+ outbound campaigns FAIL at ColdIQ. Most of the time, it wasn't the copy, timing, or offer. It was THIS... They were aimed at people who were never going to buy anyway. Here's what I mean: Too many companies still run outbound like this: → Pull a lead list from their CRM → Hope and pray something sticks → Fire off 100 cold emails/week to "hit quota" They have no idea why prospects are on their list in the first place. If you're not starting with the right inputs, it doesn't matter how good your cold email is. It's still a shot in the dark. One way to fix this is through intent data: Here are some signal plays we run for ColdIQ and our clients: 1️⃣ First-party intent: Who's visiting your website Not everyone fills out a form, but that doesn't mean they're not interested. We use tools like Instantly.ai and Vector 👻. They track anonymous visitors and identify who's checking out our content, landing pages, or product pages. This gives us a warm list of people who are already aware of us. Even if they haven't raised their hand yet. First-party intent can also come from: → Product usage (Common Room, Pocus) → Social engagement (Teamfluence™, Trigify.io) 2️⃣ Second-party intent: Champion job changes Let's say someone loved your product at their old company. They just switched jobs. Now they're in a new buying position, possibly with budget and urgency. Tools like Common Room and Unify help us track job changes across our network and historical CRM contacts. We can re-engage with a hyper-relevant message, right when they're getting settled in. Second-party intent can also come from: → Review sites (G2, Capterra) → Affinity signals (Crossbeam, WorkSpan) 3️⃣ Third-party intent: Research at scale Most often, you need to go outbound into entirely new territory. That's where third-party data comes in. Pulling insights from: → Hiring trends (LoneScale, Mantiks, PredictLeads) → Tech stack changes (BuiltWith, Similarweb) → Funding rounds (PitchBook, Crunchbase) OR from custom AI agents (Relevance AI, Claygent) We use Clay to build many of these workflows: → Filter for buying signals → Enrich contacts in real-time → Combine multiple data sources → Score and segment dynamically The result? You're increasing your odds of reaching out to the right person, with the right message, at the right time. Better targeting = better reply rates = better pipeline. Whenever your outbound is underperforming, start by reviewing your data strategy. What intent signals are you tracking in your GTM motion right now? 👇

I'm sorry, but marketers need to stop letting paid media platforms decide who sees their ads based on the limited understanding of their customers.   (I'm not sorry)   These platforms are black boxes controlling billions in ad spend that make assumptions about your audience that miss >60% of actual purchase intent signals.   Instead, you should be using verified transactions and behavioral shopping data—the strongest predictor of future purchases—to determine who sees what ads and when.   Purchase behavior shows you what people actually buy, not just where they browse or what vague demographic bucket they fit into. It reveals both intent and optimal timing windows for when customers are most likely to buy.   Let me break this down with 2 real examples:   1. When someone buys swim trunks and sunscreen, they're not interested in beach products someday. They're interested right now. Maybe they're planning a trip. That's your window to target them for sunglasses, travel kits, or vacation gear while they're actively in purchase mode.   2. When someone buys an eco-friendly mattress, they're in a home upgrade cycle. This creates a time-sensitive opportunity window where they're most receptive to other home-related purchases like non-toxic cookware, bamboo bedding, or upcycled furniture.   This timing signal, on top of seeing what a customer is purchasing, is everything. This reveals both intent and optimal timing windows.   The problem? Most businesses don't have access to this level of data. Most are stuck with their siloed 1P data. Some rely entirely on the ad platforms to optimize their spend. Few leverage collective consumer intelligence to get the most out of their marketing dollars.   The real opportunity lies in building your own data intelligence strategy instead of playing by platform rules.   The future belongs to marketers who embrace this approach.