Home Data-Driven Thinking Today’s Predictive Algorithms Are Still Better Than Humans

Today’s Predictive Algorithms Are Still Better Than Humans


jeremystanley“Data-Driven Thinking” is written by members of the media community and contains fresh ideas on the digital revolution in media.

Today’s column is written by Jeremy Stanley, chief data scientist at Sailthru.

Predicting the future is not easy.

Yet predictive algorithms are commonly criticized because they fail to perfectly foresee very rare events. That is because rare events are just that: uncommon and subtle. Asking a predictive algorithm to perfectly identify the 1% of consumers who will purchase a specific product is a wildly unrealistic expectation.

Keep in mind that, even with all the big data available today, these solutions are trying to predict human behavior. Humans are complicated, and there are billions of us all behaving in increasingly interconnected ways. Despite what Hollywood might lead you to believe, setting the expectation that an algorithm can predict our future behavior with anything near complete certainty is a fool’s errand.

So rather than looking to predictive algorithms to make definitive predictions, we should instead ask how much better is an algorithm at identifying these rare events than random guessing alone?

Consider this example of a predictive algorithm that identifies users likely to make a specific purchase for an ecommerce site. Group A, identified by an algorithm, represents 5% of consumers with a 20% average chance of purchasing a product. Group B is the other 95% of consumers with a 0.0001% chance of purchasing the same product. Random selection of 5% of users from the entire population would only generate a group with a 1% chance of purchasing, so in this example the predictive algorithm generates 20 times lift (20% / 1%) through its selection of the 5% most likely to purchase.

In other words, it found the 5% of users who are 20 times more likely to purchase than the average consumer, even though it’s still only going to be right two out of five times. With the right data and sciences, generating this kind of lift is well within the capabilities of an ecommerce predictive model.

You might critique this approach because it represents a low bar for a standard – the algorithm just had to beat random guessing. You might think that surely, a better measure would be to compare the algorithm against a human’s ability to identify these optimal users. In some domains where there are highly trained individuals who can analyze every single consumer with great care to predict outcomes, such as health care, that is a valid point.

However, in general, there are several key differences between algorithms and humans that land in favor of the use of algorithms:

Cognitive bias: Humans are horrible at making predictions. We are often blinded by an exhaustive list of cognitive biases, such as bandwagoning, self-serving bias, illusion of validity, stereotyping, the empathy effect and suggestibility.


AdExchanger Daily

Get our editors’ roundup delivered to your inbox every weekday.

Scalability: Let’s say an expert is able to make a meaningful prediction every half hour. However efficient or knowledgeable he or she may be, this is still unscalable when thousands or hundreds of thousands of predictions are required in complex ecommerce and media organizations.

Time to predictions: Training an expert can take years or even decades before they can make valuable predictions. With modern computing and algorithms, training an accurate predictive model can be done in minutes.

Self-awareness: Not only do algorithms provide meaningful lift in the accuracy of their predictions, but they can also tell us how certain they are, such as whether a particular consumer is within the segment with a 13% chance of purchasing. Humans are terrible at estimating how certain they are. We almost always overestimate our certainty by wide margins.

In the end, we need to better understand and have realistic expectations of the abilities of predictive algorithms. They can be an incredibly powerful tool. When combined with software automation and accurate user data, they can provide highly personalized experiences to users that are far superior to a one-size-fits-all or a human expert-curated approach.

Just because they aren’t perfect, we shouldn’t fool ourselves into thinking they aren’t incredibly valuable.

Follow Jeremy Stanley (@jeremystan), Sailthru (@sailthru) and AdExchanger (@adexchanger) on Twitter.

Must Read

Comic: TFW Disney+ Goes AVOD

Disney Expands Its Audience Graph And Clean Room Tech Beyond The US

Disney expands its audience graph and clean room tech to Latin America, marking the first time it will be available outside the US. The announcement precedes this week’s launch of Disney+ with ads in Latin America.

Advertible Makes Its Case To SSPs For Running Native Channel Extensions

Companies like TripleLift that created the programmatic native category are now in their awkward tween years. Cue Advertible, a “native-as-a-service” programmatic vendor, as put by co-founder and CEO Tom Anderson.

Mozilla acquires Anonym

Mozilla Acquires Anonym, A Privacy Tech Startup Founded By Two Top Former Meta Execs

Two years after leaving Meta to launch their own privacy-focused ad measurement startup in 2022, Graham Mudd and Brad Smallwood have sold their company to Mozilla.

Privacy! Commerce! Connected TV! Read all about it. Subscribe to AdExchanger Newsletters

Nope, We Haven’t Hit Peak Retail Media Yet

The move from in-store to digital shopper marketing continues, as United Airlines, Costco, PayPal, Chase and Expedia make new retail media plays. Plus: what the DSP Madhive saw in advertising sales software company Frequence.

Comic: Ad-ception

The New York Times And Instacart Integrate For Shoppable Recipes

The New York Times and Instacart are partnering for shoppable recipe videos.

Experian Enters The Third-Party Data Onboarding Business

Experian entered the third-party data onboarder market on Tuesday with a new product based on its Tapad acquisition.