As we saw in our last blog post, bots are eating digital ad budgets to an unacceptable degree. Let’s do something about it.
We have developed a predictive model that processes the massive number of signals from the digital ecosystem to predict who will buy….not who (or what!) will click. Buying includes on AND offline purchases (in this case; subscribing to a new service and paying at least one invoice); so this model varies significantly from ones developed on digital data alone.
The model was tested for a telco client for a campaign designed to acquire new customers. Channels included both search and digital display.
We found a very large difference in the activation rates (number of customers divided by households) between groups that scored highly likely to buy (and therefore recommended) and those that scored much lower.
Targeting recommended higher scoring groups led to an activation rate that was 2.1 X higher than recorded for other parts of the audience. But the overall targeting for the campaign, outside of the model, and based on chasing clicks, saw 70% of the budget go to low, out of target groups.
The path to improvement is clear: focus on in-target, high scoring groups. Given the digital inventory available to us, the entire budget could be spent there to secure these much better results.
In the battle against bots, we can have our cake and eat it too. We can keep money out of the hands of unscrupulous bot owners and in the hands of reputable digital publishers. AND we can improve performance, selling to real people who have a real interest in what we have to say. Win-win.
To learn more about how Bots Don’t Buy can help your digital marketing, contact us here.
The digital ad display market has been plagued with issues, but it should still be an important channel for all marketers, both to build sales and to build brand.
The challenge is to overcome 5 problems:
1. Bots eating ad budgets
· According to Google, 56% of ads are never seen by a human
· A study by Forrester found 69% of brands spending $1 million per month reported that at least 20% of their budgets were being lost to digital ad fraud
2. Lack of respect for people’s privacy
· an industry focused on surveillance has created the largest consumer boycott in history…ad blockers
· at the same time, new privacy regulations in Europe, the US and Canada demand transparency and restrict the use of personal data
· Google will deprecate the third party cookie in Chrome browsers in the near future and Apple’s approach to email and ad permissions will greatly restrict some common practices
3. Bad, unreliable measurement and attribution
· digital attribution tools impose a rule on clickstream data, vs using that same data to intelligently determine cause and effect.
· some digital attribution tools pretend offline media doesn’t even exist!
4. Targeting without context
· When marketers don’t develop media plans with synergy in mind…how channels can reinforce each other, vs cannibalize…budgets are wasted
· cross-channel impacts can add a double-digit boost to performance…added impact without added budget
5. No forecast capability
· common digital planning tools are not predictive at all, let alone predictive of the incremental lift digital can have in the presence of offline channels
Navigation ME is pleased to announce we are launching a solution to these problems. Since bots don’t buy, our models will act as filters to avoid ad fraud. These models focus on signals (plentiful in the digital ecosystem) that differentiate human traffic, associated with purchases, from click traffic from bots…that never buy. These patterns allow us to focus digital ads on target audiences that are disproportionately driving sales volume lift and avoid audiences that will spend little to nothing with your brand.
In addition, our new predictive and optimization models are designed to drive incremental sales from digital ad buys. Since we will use privacy compliant data, we avoid making the problem of invasive tracking worse. And since our models don’t need personal tracking to determine cause and effect, we can help you avoid regulatory problems…and keep a cleaner conscience. Most importantly, these models integrate data from offline media, so that we can quantify digital ad lift without making attribution errors. We also, in this way, take full advantage of the synergies that exist between channels that are hard to measure but powerful in effect.
We believe the digital display marketplace can be rehabilitated; and turned into a reliable growth engine for your brand. To find out more, contact us here.
Every marketer must make a decision as to how much to spend on each channel of communication available to them. In our experience, budget goes to…and stays with…channels that consistently deliver measurable results at a par or better than any other channel available. But many marketing teams today are overworked and understaffed. They need channels that are easy to plan and buy, delivering those results with less risk and less effort than competing alternatives.
Digital platforms have done an excellent job at making it easy to plan and buy. (delivering profitable results? not so clear). This post will focus on how a channel that has been with us for a very long time…Neighbourhood mail…was re-invented by adding custom AI tools, to become a profit machine.
We will look at a case involving a telecommunications company, selling Home Phone, Internet Service, Mobile and Bundles (combinations of services at attractive prices). The company’s competitive advantage is price; they offer services at a 20-30% discount to national major brands at comparable quality.
Before using Neighbourhood Mail, the company relied on digital campaigns, especially search, to sign up new customers. While the success rate of such work was acceptable, volumes were not. Neighbourhood mail was considered as a channel that could deliver reach to all serviceable households in their footprint, and sign up customers at an attractive cost.
Often Neighbourhood Mail is targeted by demography or region, and used as a media to reach a lot of households. But for this case, such an approach yields poor results; more precision in targeting was needed to generate a good result.
To support this effort, Navigation ME built a set of models, each of which predicted, for a given time period, the activation rate (number of new customers divided by pieces mailed) for a given postal walk (the unit of NM delivery) for a given product.
In building these models, we found that many factors affected activation rate:
How many times we had sent mail about a given product to that postal area, and how recently (or how many times we had sent mail about another product)
Impact of other channels used in the same areas at the same time
Demography; including income, family structure, and age distribution
The baseline of demand for a given product
Pricing vs competitive alternatives
The penetration of current customers in that area, and the trend; was new customer acquisition outpacing churn, growing penetration? How quickly? Or was it the reverse; we are having trouble keeping customers in that area and replacing them when they go
The difference in predicted activation rate, and therefore cost-per-activation, was large; top deciles were often at 4x as high an activation rate as the 5th decile; and the bottom deciles typically delivered hardly any activations at all. (note; the measurement of activations took into account multi-channel effects, isolating the impact of Neighbourhood Mail for better decision-making). Model accuracy rates, from pre-campaign scoring to post-campaign evaluation, are consistently in the 92-95% range.
The cost of delivering a given service depended on its footprint. This meant that since we wanted to calculate the predicted profit of mailing a given postal area, we needed to know the cost of delivery in that area.
We found that churn was not uniform in all areas; there was large variation with some neighbourhoods consistently churning at higher rates. We needed to take this into account as well, since the value of a new customer from those areas would, all other things being equal, be less than in areas that showed lower churn risk.
For each postal walk, we had 7 scores; one for each product/footprint combination. For a given postal walk, the score for one month would be different depending on whether we mailed the previous month or not.
To avoid this level of complexity from overwhelming decision makers, we added our custom optimization algorithm, tasked to find the optimal distribution of mail:
For each postal walk…
…for each of the three months of the campaign…
…for each product…
This meant some postal walks could get Product A for months 1 and 2, and Product B for month 3. Or a given walk might not get any mail at all, if the model predicted the costs would exceed the profits of the predicted number of new activations.
Interestingly, about 1/3 of new activations came from existing customers, something the model picked up by taking penetration momentum into account. So in this case, Neighbourhood Mail became not only a profitable new customer acquisition channel, but a good cross-sell channel as well.
For planning purposes, we created an ROI curve:
Each point on the curve was the result of the model doing an optimal allocation of available budget across waves, time, and product. All the work of taking full advantage of the model’s learning and accuracy was done for the planners by the software.
Since there is no free lunch, the curve flattens as more pieces are added. This reflects what we know about all advertising; after a given point, additional touches add nothing to business outcomes.
The ROI curve enables a planner to increase spend with confidence of the outcome (risk can be calculated explicitly for each scenario). It also demonstrates the overall impact of this channel; for a mailing of 2.5 million pieces, for example, a profit after all variable costs and campaign fixed costs are paid of over $4.5 million is generated.
We have been running this system for this client for many years; with results in line with model expectations each time. Predicted vs actual is carefully tracked by decile so we know the model continues to track today’s market conditions.
Taken together, the reach of Neighbourhood Mail plus the decision-making impact of Navigation ME’s predictive and optimization models has created a profit machine…high performance, with consistent results, at low risk and that is easy to plan for.
(Or the optimization bonus, or the budget multiplier…these blog post titles require a lot of thought…)
Imagine this scene: the CMO goes to see the CFO. “This economy is tough…I need more budget to hit my KPI target.”
The conversation does not go well. Not only does the CFO not want to approve more budget, they want to CUT budget, to “protect the bottom line”.
If this, or something like this, has happened to you (or a friend) then chances are you are not using a technology that I would like to talk about today…predictive optimization.
Predictive optimization combines two analytical tools; predictive modeling and customized optimization algorithms.
The idea is to capture the dynamics of your business with an accurate predictive model, and then use that model to drive simulations in which we vary spend allocations (by channel, time and market, typically, although other factors can be simulated as well). One of those allocations is identified by the algorithm as optimal; that is, the highest KPI effect for the money spent over the time period being planned. (we will come back to that point, below).
The key to making it work: model accuracy.
Aim to have your model explain a very high percentage of variation in past behaviour. Most of our implementations use models that are over 90% accurate when we compare predicted to actual on recent time periods (yes, including the post-COVID period; see our last blog post here)
Integrated marcom campaigns behave in complex ways; we want our models to capture these effects. But the price we pay for that accuracy is to have a complex model. Think about the dynamics it must account for:
Diminishing return effects overall and by channel
One of the few “laws” of marcom planning is the diminishing return effect. As you increase spend, there comes a point where each additional dollar has less and less an effect. In our experience, this applies not just to the overall spend in the campaign, but to individual channels as well. A planner needs to know where each channel is on its curve for the spend proposed.
We ideally want the channels we pick to reinforce each other’s impact in the market. Generally, the more channels we have, the better the effect, but to a limit. What we absolutely must avoid is cannibalization; the effect of spend in one channel diminishing the contribution of another channel.
Marcom has an effect over a period of time, as we all know. What is less well known is how that period varies by channel and by creative within channel. Brand ads tend to have an impact over a longer period of time; promotion/call to action shorter. Most digital forms have very short effect periods while other channels impact over a longer period
Local geographic effects
Retailers and other location based marketers must take into account the impact distance to store has
What is the right balance of brand vs promotion? Budget allocation across different creative executions?
With all this (and more) going on, I just don’t see how planners can put together a campaign that takes full advantage of these effects without tools like predictive optimization.
Further, to give guidance to decision makers, it is important to be able to produce credible, accurate forecasts of KPIs that will result from a given plan. That is a big advantage of using a technology like predictive optimization. It is one of the aspects of the technology that is most important in bringing the CFO onside. Once they see the accuracy of the model, it is easier to trust it to help with decisions like these.
In our experience, this approach can lift KPIs by double digit amounts, while keeping budget constant. Or, it can offset some or all of the effect of a budget cut. Or, it can make a persuasive case for a budget increase.
More impact on the same budget? That’s the free money effect. We think predictive optimization has a key role to play in helping brands recover in this tough COVID economy.