Data-Driven Marketing Approaches

Incrementality testing is crucial for evaluating the effectiveness of marketing campaigns because it helps marketers determine the true impact of their efforts. Without this testing, it's difficult to know whether observed changes in user behavior or sales were actually caused by the marketing campaign or if they would have occurred naturally. By measuring incrementality, marketers can attribute changes in key metrics directly to their campaign actions and optimize future strategies based on concrete data. In this blog written by the data scientist team from Expedia Group, a detailed guide is shared on how to measure marketing campaign incrementality through geo-testing. Geo-testing allows marketers to split regions into control and treatment groups to observe the true impact of a campaign. The guide breaks the process down into three main stages: - The first stage is pre-testing, where the team determines the appropriate geographical granularity—whether to use states, Designated Market Areas (DMAs), or zip codes. They then strategically select a subset of available regions and assign them to control and treatment groups. It's crucial to validate these selections using statistical tests to ensure that the regions are comparable and the split is sound. - The second stage is the test itself, where the marketing intervention is applied to the treatment group. During this phase, the team must closely monitor business performance, collect data, and address any issues that may arise.  - The third stage is post-test analysis. Rather than immediately measuring the campaign's lift, the team recommends waiting for a "cooldown" period to capture any delayed effects. This waiting period also allows for control and treatment groups to converge again, confirming that the campaign's impact has ended and ensuring the model hasn’t decayed. This structure helps calculate Incremental Return on Advertising spending, answering questions like “How do we measure the sales directly driven by our marketing efforts?” and “Where should we allocate future marketing spend?” The blog serves as a valuable reference for those looking for more technical insights, including software tools used in this process. #datascience #marketing #measurement #incrementality #analysis #experimentation – – –  Check out the "Snacks Weekly on Data Science" podcast and subscribe, where I explain in more detail the concepts discussed in this and future posts:    -- Spotify: https://lnkd.in/gKgaMvbh   -- Apple Podcast: https://lnkd.in/gj6aPBBY    -- Youtube: https://lnkd.in/gcwPeBmR https://lnkd.in/gWKzX8X2 

Campaigns are not one-size-fits-all. Especially when you're talking to customers across different regions. Combining marketing teams into a single unit that looks after multiple geographies bring efficiency. But it also introduces complexity—because what works in New York won’t always land in New Delhi. So, how do you really connect with customers across such diverse markets? You test. Run localized market experiments to uncover: What benefits resonate most in Texas versus Toronto. How value propositions shift between Sydney and Singapore. What creative actually feels culturally relevant (not just translated). Here’s how you get it right: - Test benefits, messaging, and cultural fit on live platforms like Meta or LinkedIn using Heatseeker. - Use behavior-driven insights—CTR, CPA, engagement metrics—to guide decisions. - Stealth test where needed to mitigate risk and gather unbiased feedback. - Optimize campaigns iteratively to scale what works, fast. The result is campaigns that speak the language-beyond just words. Data-backed insights into what drives customers in that specific local. A scalable playbook for delivering localized campaigns that convert. Your streamlined team now has the tools to drive success.

More leads don't always mean more growth. Sometimes, they just mean more wasted budget. I recently worked with a fast-growing gifting and floral commerce brand that had a common scaling challenge: High traffic. More leads. But declining conversions and rising CAC. The problem wasn't a lack of marketing efforts. It was a lack of data-driven decisions. Here's what we discovered: ❌ Lead qualification was based only on form submissions ❌ Multiple campaigns were running without clear attribution ❌ Every lead received the same nurturing journey ❌ Mobile users were bringing traffic but not converting The solution? We stopped treating every lead equally. Using behavioral data, we built a smarter lead scoring system based on intent signals like: → Pages visited → Time spent on the website → Category interest → Repeat visits Then we: ✅ Shifted budget toward high-performing channels ✅ Created personalized nurture journeys ✅ Optimized the mobile experience using real user behavior The outcome after 6 months: 📈 52% improvement in lead quality 📉 41% reduction in CAC 🚀 67% increase in revenue per lead 📱 Mobile conversion improved significantly The biggest lesson? Growth is not about generating more leads. It's about understanding the right leads. How are you using data to improve your growth strategy? #DataAnalytics #GrowthStrategy #LeadGeneration #MarketingAnalytics #DigitalMarketing #CRO

Inflation often forces businesses into a dilemma—raise prices and risk losing customers, or keep prices stable and shrink margins. But what if data could help strike the perfect balance? 🚀 Challenge: Flipkart, one of India’s largest e-commerce platforms, noticed fluctuating customer retention rates and declining repeat purchases, especially during inflationary periods. Traditional deep-discount campaigns led to short-term sales spikes but failed to build long-term customer loyalty. 🔎 Solution: Data-Driven Discounting Strategy Flipkart’s analytics team uncovered a key insight: Small, frequent discounts (e.g., 5-10% on repeat purchases) led to higher engagement. Personalized offers based on purchase history encouraged repeat buys. A/B testing revealed that customers preferred consistency over occasional deep discounts. 💡 Implementation: Using AI-driven dynamic pricing, Flipkart rolled out: ✅ Tiered discounts for loyal customers. ✅ AI-powered coupon recommendations. ✅ Targeted email campaigns promoting small, time-sensitive discounts. 📈 Results: After three months of testing, Flipkart saw: ✔️ 17% increase in repeat purchases ✔️ 12% uplift in customer retention ✔️ Higher profit margins vs. deep discounting 🎯 Key Takeaway: In an inflationary environment, data-driven pricing isn't just about maximizing revenue—it’s about customer psychology. Businesses that personalize their offers and optimize discounts intelligently can boost retention while protecting margins. 𝑾𝒉𝒂𝒕 𝒑𝒓𝒊𝒄𝒊𝒏𝒈 𝒔𝒕𝒓𝒂𝒕𝒆𝒈𝒊𝒆𝒔 𝒉𝒂𝒗𝒆 𝒘𝒐𝒓𝒌𝒆𝒅 𝒇𝒐𝒓 𝒚𝒐𝒖𝒓 𝒃𝒖𝒔𝒊𝒏𝒆𝒔𝒔 𝒊𝒏 𝒄𝒉𝒂𝒍𝒍𝒆𝒏𝒈𝒊𝒏𝒈 𝒕𝒊𝒎𝒆𝒔? #datadrivendecisionmaking #DataAnalytics #DiscountStrategy #BusinessStrategies

💪 David v Goliath.... ... How to compete using a Smart Data Strategy... The biggest brands in the category can often easily outspend competitors when it comes to investment in data & insight, and this can give them a clear competitive edge. Smaller businesses are unlikely to be able to match their spend, but they can spend *smarter* to compete more effectively. Here’s how: 🚀  1. Start with High-Impact Data ↳ Market Overview Reports: Affordable sources like Mintel or Euromonitor provide a snapshot of market size, trends & competitor positioning. This helps identify category trends & establish the right areas or Shoppers to target without the ongoing cost of continuous data feeds. ↳ Focus on Key Business Questions: Pinpoint where insight will make the biggest impact e.g. - Detailed understanding of Retailer category performance ahead of a range review to help secure new distribution. - Identifying target consumers & optimal outreach strategies to boost penetration. 🔍  2. Leverage Selective EPOS & Loyalty Data ↳ Market-Level EPOS Data: This can be invaluable for insight into category dynamics & benchmarking KPIs vs competitors whilst avoiding high costs of retailer-specific feeds. ↳ Loyalty Card Data: Although this will only cover one retailer (so no total market read) it can give you very granular insights on sales performance as well as WHO is buying your brand. 🎯 3. Focus on Actionable Insights ↳ Prioritize Impactful Data: Concentrate on insights that can directly drive product development, pricing & promotions. Avoid ‘nice-to-have’ data that doesn’t materially impact your business. ↳ Make the most of the data you need DO have: Manage scope to only buy the data you *need* & make sure each source is *fully* mined. Investing time in analysis instead of buying new data can yield deeper understanding & more opportunities to optimise your brand performance. 📈 4. Scale Data Investments with Business Growth ↳ Mix One-Off & Continuous Feeds: Start with one-off data sources, then add targeted continuous data feeds as you scale. Regularly review usage & actionability & stop reports which don't add value. 🧠 5. Outsmart, Don’t Outspend --> Be Agile ↳ Develop a *Learning* culture : Smaller businesses can move around the Build/Measure/Learn loop much faster than bigger brands - Insight is the rocket fuel you need to power this. Key Takeaway: Strategic Data Use Although small & medium sized businesses will inevitably have less data, if they use what they can afford to answer the right questions & act quickly to execute then they can find a competitive edge of their own. What are your thoughts & experiences - let us know in the comments. Want to find out more? This week's #CategoryWins newsletter digs into this subject in much more detail : See link in comments or my bio ♻️ & if you enjoyed this post, please like & share it with your network. #CategoryManagement #FMCG #CPG #DataStrategy #CompeteSmarter

Meta, Google, TikTok, and other ad channels are misleading you. Third-party attribution tools like Triple Whale and North Beam aren't better—they’re flawed too. Tracking has always relied on estimated models, not hard numbers. After iOS 14, tracking became harder, leading to a surge in third-party solutions. But these also provide conflicting data, making it tough to find the truth. So, what is the truth? The only reliable way to measure your marketing efforts is through incrementality tests. These tests answer the question, "What if this channel or ad never existed?" By showing ads to one group and withholding from another, you can measure the true impact on revenue and profit. For example, if you're running Facebook ads and selling on Shopify and Amazon, incrementality tests reveal how Facebook ads impact Amazon sales. Without the initial Facebook touchpoint, an Amazon purchase might not have happened, even though traditional attribution wouldn’t show this. This is why ROAS and third-party attribution aren’t accurate. They use models that can be thwarted by privacy settings and cross-channel purchases. By running incrementality tests, you discover the true impact of your marketing efforts. We ran a 14-day Meta holdout test and found that zip codes shown ads generated 50% more Amazon revenue than those not shown ads, despite sending traffic to Shopify. Now is the perfect time to run these tests. Q3 is calm, free from major holidays that skew results. This is your chance to optimize before Q4. If your brand generates seven figures annually, this should be a top priority to grow profits in Q4.

Using last touch attribution to measure brand impact is a failed state. It should not be complicated to measure the impact of brand advertising and its impact on performance marketing. Companies resist by saying the opportunity cost of doing so means lost revenue. Then pick an intercontinental effort apart when the attribution tells a poor or fuzzy story. Testing via geo holdouts will tell you how your brands efforts perform compared to abstaining from them at all. Here’s an example how: You have a new product line to launch from a recent M&A. Say you want to launch it widely to financial professionals. No account list here. Just Director level finance professionals and above. Here’s exactly how I would design testing this launch promotionally to make a bet on brand advertising and prove whether it worked (or didn't). First, pick 4 similarly sized DMAs:   Boston or San Francisco.  Atlanta or Houston. Miami or Denver. Run wide and broad brand advertising picking 2 between Boston, Atlanta, and Miami. Target, choose, and run your brand ad mediums. CTV. YouTube. Podcast Ads. Radio. OOH. Anything designed where a clear call to action is not programmable through an action (click, etc.). Then run direct response in both the Test and the Control DMAs.  Trial Offers. Webinars. Gift Card Demos. Pilot Offers.  Cold Email. Cold Outbound. Convo Ads. Lead Gen Ads. Something where you ask the market to commit to you. Budget the same for each market served for the performance marketing to keep spend equal. Brand advertising is distributed evenly across the test DMAs. Budget 40% of the total test budget for the brand effort and 60% for the performance. With $400K across 4 months for this launch to promote you put $160K into brand advertising across 2 DMAs ($80K per DMA) and $240K in direct response across 4 DMAs ($120K per DMA). Run this for 2-3 sales cycles (120-180 days). Measure conversions, sales accepted leads, opportunities, and sales qualified opportunities in each market afterward. Measure the difference between DMAs, both attributable and non-attributable. Voila, you have designed a real test to assess the lift of brand advertising for your product launch, and can apply that learning to future campaigns. For companies with upper six figure and above media budgets, these are the kinds of media tests where you don’t lose your opportunity cost of promotion to your market while knowing how much your brand efforts lift your overall performance. What about this kind of test would fail assuming the ability to track the conversion at the DMA level is not a difficult thing to do?

Your product hit its ceiling. Or it didn’t, ...and your last scale test just measured the wrong thing. Here’s how to tell. We see brands run the same test all the time: Increase the budget. Let spend climb for a few weeks. Pull it back. Then check whether total sales changed. If sales barely moved, they assume the product is maxed out. But that conclusion only works if the extra spend created new demand. Most of the time, it didn’t. When budgets increase without clear controls, Amazon pushes more spend toward the easiest conversions. Usually, that means: • Branded search terms • High-ranking keywords you already own • Retargeting existing shoppers • Product pages already converting organically The account reports more ad sales. But the business may not be generating more total sales. You are paying to capture demand that already existed. Then you reduce the budget. Sales stay relatively stable. And the test gets labeled a failure. The product did not necessarily hit its ceiling. The test simply measured how much existing demand you could turn into attributed ad sales. Here is how we structure a cleaner scale test: 1. Separate branded traffic Put branded exact-match terms in their own campaigns. Keep their budgets controlled. Do not let them absorb the additional scale budget. 2. Choose the demand you want to create Select a small group of high-relevance, non-branded search terms. These should be keywords where improving rank could realistically unlock more sales. 3. Establish a baseline Before changing anything, record: • Total sales • Organic sales • Ad sales • TACoS • Keyword rank • New-to-brand sales • Conversion rate 4. Add budget to the test campaigns only Do not increase spend across the entire account. Scale the specific keywords, placements, or audiences you are testing. 5. Measure the business result Do not ask only: “Did ad sales increase?” Ask: “Did total sales increase?” “Did organic rank improve?” “Did non-branded sales grow?” “Did the lift remain after spend normalized?” That is the difference between a real scale test and a branded defense campaign with extra steps. A bad test tells you the product has no room left. A good test tells you where the next layer of demand can come from.

There's a one-week test we run on every Amazon ad audit we do here at Nectar. It finds wasted branded spend faster than any other analysis we do. The test: cut branded campaign spend in half for one week. Then check what your branded purchase share did. If share holds, the dollars you cut were paying for clicks you would have captured organically. We've run this on enough accounts to know the pattern. Branded purchase share typically holds at 90 to 95% regardless of how much you spend. Everything above that inflection point is wasted budget defending traffic you already own. How to run it: 1. Pull your branded campaigns and your 4-week average branded purchase share from Search Query Performance. 2. Cut weekly branded spend by 50% for one full week. Don't pause, halve. 3. Compare that week's purchase share to the 4-week baseline. 4. If share moves less than 2 points, redirect the cut dollars to non-branded category terms with low impression share and high search volume. The whole test takes one week. The reallocation pays for itself in the first month. Most teams won't run it because their reporting can't isolate branded purchase share at the keyword level over time. Search Query Performance gives you that data weekly, on brand and on competitors. In 2026, brands running this test will widen the gap with those still defending branded spend that isn't delivering results.

One of the key pillars of a successful demand generation strategy is a diversified marketing mix. Recently, I had the opportunity to work with a client who initially relied heavily on just two channels—SEO and Paid Ads. Within 6 months, we transformed their approach from a two-legged strategy into a well-rounded marketing mix that now drives revenues from multiple sources. And we’re just getting started! How did we achieve this? ➡ Holistic Data-Driven Analysis: We began with a comprehensive audit of their current marketing efforts, identifying gaps and opportunities across various channels. A significant part of this was convincing the C-suite why relying on just two channels is a dangerous strategy. ➡ Targeted Channel Expansion: Instead of relying solely on SEO and Paid Ads, we expanded into Email Marketing, Social Media, and Referral Programs. Each channel was carefully selected based on the client’s audience and business goals. For email marketing, we created custom flows for both current customers and prospects, building an engaged audience through just-in-time, educational, and transactional emails. ➡ Consistent Messaging & Cross-Channel Synergies: I'm a firm believer in Ogilvy's "The medium is the message," so we ensured the brand message remained consistent across all channels. This created a seamless experience for the audience and strengthened the brand’s presence. We also ensured that channels like email and social media reinforced one another, driving stronger brand presence and conversions. ➡ Data-Driven Adjustments: Linear attribution by channel is outdated, so we had to first "sell" the idea of assisted attribution to the client. In our omni-channel world, it was crucial to analyze data and make campaign adjustments based on those insights. By closely monitoring performance metrics, we quickly optimized our strategies for the best ROI across all channels. ➡ Collaboration and Buy-In: As marketers, our real "selling" begins after onboarding a client, as we're constantly pitching new ways to drive demand. Achieving this transformation required strong collaboration with the client’s internal team and stakeholders. Together, we aligned on goals, brand positioning, and data insights to drive initiatives forward. Looking back, we could’ve taken the safer route of only managing the client’s paid media and organic search efforts, but that would’ve been short-sighted. Instead, we took a slightly riskier approach by launching new demand generation initiatives that might have got us fired, but it was in the best interest of the business. This strategy not only diversified their revenue streams but also made their marketing efforts more resilient and adaptable to changing market conditions. Would love to hear your thoughts....what are your greatest challenges with demand generation marketing?