Library

A UK field experiment with 110,000 drivers found that a 40% lower price increased the electricity that drivers bought through an app by 117%. About half of that increase came from drivers who left other payment apps.

A study of more than 60,000 US households found that TV ads had more than 2 times the effect on frequent buyers. Ads remind people of a good past experience.

A Facebook test with about 1 million users found that opposing comments increased link clicks by 14.9%. A second test found that the same comments decreased donations by 7.5%.

A field test with about 1 million app users found that clicks caused only about 34% of the effect of a push message. Learn how to measure the other 66%.

When an AI chat recommended a book, 61.2% of people chose it. When the same book was only first in a list, 22.4% of people chose it.

In 3 experiments with 76,977 people, AI messages with facts and evidence persuaded 27% more than basic messages. Personal details about the reader added less than 1 point on a 100-point scale.

In a 7-day test with 1,100 Google users, search with only AI answers decreased satisfaction, trust and the number of searches. Keep the normal search results next to your AI answers.

A test with more than 20 million customers found that a discount chosen for each customer increased revenue by 4.5%. The new method sent small or large discounts. It did not send the same medium discount to all customers.

A study of 305,121 display ads found that AI images got as many clicks as human images on average. But ads that looked AI-made got fewer clicks.

Thousands of A/B tests at Bing, startups and public programs show how to test. They also show what results to expect. They help you avoid results that look good but are not real.

Field experiments with consultants, developers, writers and support agents show where AI helps and where it causes problems. They also show who gets the most benefit.

We changed field studies into rules for a sales team. The studies are about reply time, first offers, commissions, price advice, gifts, apologies and feedback.

Large ad experiments at eBay, Facebook, Yahoo and Pandora show how much ads really earn. They also show how to check your own ads.

We changed field experiments with hundreds of thousands of customers into rules for your email list. The studies are about subject lines, how often to send, reminders and sharing.

We changed 8 field and lab studies into rules that you can use this week. The studies show how people react to prices, plans, trials and free offers.

A test with about 50,000 donors found that a matching offer increased the money from each letter by 19%. A 2-to-1 or 3-to-1 match did not collect more money than a 1-to-1 match.

A random test with 1,612 staff at Trip.com found that 2 home days each week decreased quit rates by 1/3. Performance and promotions did not change over 2 years.

In a random test at large Indian textile firms, free advice on basic management increased productivity by 17% in the first year. The changes were simple. They included tracking, maintenance and stock control.

In a 9-month test at the Chinese travel company Ctrip, call center staff who worked from home performed 13% better. Half as many of them left the company.

In a study of about 20,000 coin flips, people who got a coin result for a big change made the change more often. After 6 months, the people who made the change were happier.