4 Ways Human Behavior Forecasting Is Being Applied in Business Analytics

By Melissa Todisco, January 6, 2020

Human behavior forecasting is not a new concept. Facebook predicts what ads you are more likely to click on. Google suggests what you might be searching for. Netflix tells you what other shows you might like to watch. All of them are using the power of artificial intelligence to predict an individual’s needs and preferences.

 

We define human behavior forecasting as the endeavor to anticipate (within some margin of error) the choices that people make. Choices are what products to buy, what leisure activities to engage in, what media to consume, what mode of transportation to use, etc. Whenever people are faced with multiple alternatives differentiated through multiple attributes, human behavior forecasting applies.

 

But what if you could predict how a group of likeminded people are likely to behave and use that to forecast business results? What if you could simulate how people are likely to respond to an idea – a new product, a new marketing campaign, a new offer? Market simulation is emerging as a way to forecast how populations of people will behave and how that behavior is likely to effect business outcomes. 

 

Market simulation is made possible through the unique blending of agent-based modeling, behavioral economics and network science. These three sciences make it possible to simulate how a population of agents will behave and make choices between two or more alternatives. When attribution and machine learning are also applied, this allows organizations to find patterns between human behavior and business activity.

Because of its strong theoretical foundations, market simulation offers a lot of explanatory power. Similar to how meteorologists may use a weather simulation to test theories of weather formation, business analytics teams are now turning to market simulation software to test strategies to make the right decision about how to allocate resources. 

How does market simulation differ from other types of forecasting?

 

Other forecasting methods, like macroeconomic and regression models, typically make a few or all of the following simplifications:

 

  1. Populations can be reduced to one representative agent
  2. Agents are perfectly rational
  3. Feedback loops can be ignored or treated as exogenous factors
  4. Economic markets are priced at equilibrium

 

Market simulation breaks each of these assumptions.

 

For instance, an ARIMA model of sales at Widget Co. ignores who is doing the buying — unless the data is comprised of individual purchase histories. Thus, it reduces a population to one agent. If market simulation was applied to this same problem it would attribute the sales to a population of buyers who are allowed different motives, behaviors, locations, friends, etc.

 

Recommendation engines have been wildly successful navigating the illogic and quirkiness of millions of users’ cultural tastes. Their personally tailored predictions are the precise opposite of assuming a population is homogeneous. In the beginning, these recommendations considered each choice and each user in isolation. Now the engines are incorporating social networks and internet “virality”. Since popularity is a feedback from other people’s actions affecting the next user’s choice, the engines are moving closer to the human behavior forecasting definition.

 

The dynamic stochastic general equilibrium model of macroeconomic forecasting assumes households and firms plan infinitely into the future and precisely optimize their long-term goals. By contrast, a human behavior forecast’s agents are allowed limited memory, limited forethought, and limited brainpower. And instead of assuming prices and other economic indicators play out to a purely logical conclusion, outcomes will emerge in the forecast as a result of all these interacting behaviors.

 

By incorporating more realistic detail into the model, market simulation reproduces a wider variety of phenomena than other methods. Forecasts will also maintain their validity further into the future, especially for topics involving intra-population interactions, rapidly changing industries, or path dependencies, because these effects build up over time.

 

How businesses are applying market simulation

 

Many analysts are predominantly trained in the theories of statistics and AutoML, and are less familiar with agent-based modeling and simulation. Using market simulation software, citizen data scientists are enabled to forecast human behavior of entire populations and simulate markets using a pre-built algorithm and workflow that allows them to set the parameters of their market to address a specific need.

 

Here is a list of some common business needs it is being used to address:

 

Consumer Marketing Strategic Decisions: Marketers have long struggled to link marketing campaigns or branding efforts to business outcomes. Everyday, marketers need to make decisions about the best approach for influencing consumer choice. They need to choose where to place ads, what message to emphasize and find the right balance between building brand love and raising product consideration. Marketers often distrust other analytics because they are viewed as partial. With market simulation software, marketing analytics teams are able to account for human perceptions and forecast how marketing investments will influence human behavior and deliver sales, store visits, subscriptions or any other key business outcome.

Consumer Product Strategic Decisions: The role of a product team is to develop and raise awareness for a product that people want to choose more than other products on the market. Focus groups, surveys, product reviews and product usage are the typical analyses methods used to inform strategic product decisions. While useful for understanding consumer preference or perceptions, it lacks any kind of quantifiable predictive capability. Using market simulation, product teams can integrate this data to test variations in product features and design the optimal go-to-market strategy from pricing to media mix.

Entertainment Production Strategy: There is a tremendous amount of choice in the entertainment industry and the attention span of consumers is incredibly short. If a new show, movie or game can’t generate enough buzz or interest, the likelihood of achieving a reasonable audience or user size is small. Market simulation software allows production teams to evaluate how their creative choices will increase audience size and ultimately profits. Which actor will draw a larger audience? What is the right distribution strategy? How should the marketing budget be allocated?

 

Media Advertising Strategy: Media companies have long relied on audience size, demographics and ratings to sell ad space. Advertisers are demanding greater understanding of how buying ad space on one network versus another will deliver ROI to their organization. Market simulation software allows ad sales teams to share optimized media plans down to the timeslot including a forecast of the expected impact on advertiser sales.

 

These are just a few examples of where human behavior forecasting can be applied to help reduce uncertainty about strategic decisions.

RELATED CONTENT