TMCnet News
Sabio's App Science® Labs Finds: Apps, Location & Phone Price Mobile Indicators of WealthLOS ANGELES, July 18, 2019 /PRNewswire/ -- App Science® Labs, the research division of Sabio, the media and technology company behind App Science®, a proprietary machine learning platform that pairs observations of consumer behavior to corresponding data that inform marketing decisions, today announced the availability of research aimed to help better identify consumers with higher household incomes (HHI). "Many of our clients, from financial institutions and luxury automotive manufacturers to theme park vacation marketers and high-end retailers, have products and services that require we reach higher HHI customers," said Joe Camacho, CMO of Sabio. "In an effort to continue improving the mobile solutions we provide our clients, it is extremely valuable to constantly find new ways to identify their target customers more effectively. We look forward to sharing the compelling findings from App Science® Labs and how it can predict a person's financial status based on their apps, location, and the type of phone they use." Inspired by a published economics paper from the University of Chicago with the National Bureau of Economic Research, the researchers found that "no individual brand is as predictive of being high-income as owning an Apple iPhone" based on 2016 data. The iPhone is a luxury product that is usually priced higher than competing smartphones and is rising in cost with each new iteration. Generally, to afford these expensive phones, most purchasers should come from a higher income bracket. As a result, the iPhone has become the best indicator of wealth from among everyday items. Diving deeper and testing for correlations, App Science® Labs tested these demographics and iPhone findings by including location analysis and higher riced Android phones, defined as priced above $500, to see if higher priced phones were more likely owned by consumers who live in higher income zip codes as defined by the 2010 U.S. Census. The feature the team chose to focus on was the value of the phone. From the make and model, one can derive the retail price of the phone. This variable was chosen due to its economic significance, academic literature support, and easy availability. From the price of your phone, the team wanted to see how accurate phone price is in determining wealth. Since it's impossible to know each person's true income, one would have to use a viable substitute. The best and most reliable proxy found was the zip code median income. Therefore, the team predicted the relationship of a person's income to their phone by examining the relationship between the average cell phone price from a given zip code and the median income reported by the U.S. Census. After accounting for noise within the data, regression analysis shows that phone price is a statistically significant factor in determining median income. The results are strong enough to indicate that higher priced phones are more likely to belong to individuals who reside in higher income zip codes. Using these findings, the App Science® Labs team compared the results of a recent "audiobook" app download campaign which Sabio ran and that performed well above benchmarks to see how it compared to the phone price/location analysis. Camacho continued, "Given that many studies have shown the strong correlation between reading, academic success, and household income, we wanted to test to see if an audiobook app would produce similarities with respect to phone price and median income." The research concluded that there is a strong enough correlation between higher priced phones and higher household incomes, which can be used in combination with other mobile data signals including location and apps targeting up-market consumers to optimize the ad campaigns of Sabio's clients. Further App Science® research between these and other mobile data signals, and how they predict income and other segments, are necessary and forthcoming. About Sabio
SOURCE Sabio 
|
View original content: