The rise of SOAPnet was an incredible gift to teen soap fans and its fall still saddens nearly eight years later. SOAPnet launched in January 2000, just months before the series finale of “Beverly Hills, 90210.” It was conceived by the Disney-ABC Television Group to capitalize on interest in ABC’s current daytime soap operas and the soaps of yesteryear. The cable channel broadcast same-day airings of ABC’s soaps, in addition to showcasing classic soaps that had long been off the air.

Recommender systems are among the most ubiquitous Machine Learning applications in the world today. However, the underlying ranking models are plagued by numerous biases that can severely limit the quality of the resulting recommendations. The problem of building unbiased rankers - also known as unbiased learning to rank, ULTR - remains one of the most important research problems within ML and is still far from being solved. In this post, we’ll take a deep-dive into one particular modeling approach that has relatively recently enabled the industry to control biases very effectively and thus build vastly superior recommender systems: the two-tower model, where one tower learns relevance and another (shallow) tower learns biases.

These days, credit card companies are falling over one another to offer perks that differentiate them from the competition. And as part of the benefits that come with my Chase Sapphire Preferred card [1], I get occasional reports about my credit score and activity on (pause for dramatic effect) the “dark web.” Here’s an email Chase sent me today. The tone can be paraphrased as “Nothing to be alarmed about, sir, but perhaps you want to climb into your fallout shelter before you click this link.

“When they permitted you to mount your father’s throne, it was only on the assurance that you’d keep the spice flowing. You’ve failed them, Majesty. Do you know the consequences?” - Frank Herbert, Dune The 1984 David Lynch film adaptation of Dune did much to popularise the concepts of Frank Herbert’s astonishing 1965 science fiction novel. The evocative phrase ‘The spice must flow’ originates in this movie, and does not appear in the novel or its sequels.

The final scene from 1997’s My Best Friend’s Wedding still remains to be one of my favorites in the history of rom-coms.  In the scene, the main lead, Julianne Potter or “Jules” played by Julia Roberts, sits sulking in a lavender gown in a half-lit ballroom during a wedding reception. Instead of dancing happily with a husband, she is alone and has just said goodbye to the man she loved. Picked out of context, one might think this is a tragic ending to a love story.