How to Reduce Class Imbalance Bias in AI? (Explained with a Riddle)
The Riddle
For International Women's Day, Mindspace asked 22 people to solve the following riddle and recorded their responses:
A father is about to bring his son to a job interview, applying to work at a large stock trading company. The son is incredibly nervous… In the car during their drive over they hardly speak… Just when arriving at the parking lot of the company the son receives a phone call. He looks up at this father, who says: "Go ahead, pick it up." The caller is the CEO of the stock trading company, who says: "Good luck son…you've got this." The boy hangs up the phone and again looks at his father, who is still sitting next to him in the car.
How is this possible? No, really… take a minute and think about it. Alright! Final answer? ˙ɹǝɥʇoɯ s,uos ǝɥʇ sı OƎƆ ǝɥ⊥
Even though it is a straightforward answer, most people couldn't solve it. The human experience of observing that the majority of CEOs are men, especially in stock trading companies that are historically male-dominated, created the human bias of associating a CEO with a man.
Bias in Machine Learning
So, how does this relate to machine learning? Well, the same way that humans develop biases from experience, machine learning models learn biases from training data, a.k.a a model's "experience."
Class Imbalance Bias
Take, for example, a training dataset for spam detection. Usually, datasets like that are imbalanced, meaning that the ratio of data available for different classes is disproportional – typically, 10% spam and 90% ham (not spam). Although it is an accurate representation of reality (unless you signed up for too many loyalty programs
