Walmart, the world's largest retailer, acquired Aspectiva in 2019.
Aspectiva became part of a team of 2.3 million Walmart employees that collaborate to serve hundreds of millions of customers across the world.
(This, in itself, was quite a change for a small start-up from Tel Aviv! you can read a bit about it, here)
I joined the company not long after, at the end of 2019, and in my nearly two years in the new Israeli unit, here’s what I’ve learnt about the gentle giant’s culture:
Small start-ups, not giant corporations, are regarded to be at the forefront of innovation…
Criminal profiling is used by law enforcement agencies ever since ‘Jack the Ripper’ terrorized the citizens of Whitechapel at the victorian age.
But mainly, this method has been significantly used since the 1970s by the American Federal Bureau of Investigation (FBI). They have created what is today known as the detection and classification method for personality and behavioral characteristics based on analysis of the actions (or crimes) a person committed.
The method uses a sequence of identifications that help detectives build a psychological profile of an offender based on the premise that behavior reflects personality.
The process is loaded with…
In late 2019, I joined Aspectiva, an AI solution for informed shopping decisions using machine learning technology and natural language processing capabilities.
At that point, Aspectiva was recently acquired by Walmart, the world’s largest retailer. It has recently started presenting to Walmart’s users' insights from Aspectiva’s data and was in the first steps of integrating into Walmart’s infrastructure.
My past few roles have also been post-acquisition startups, but never at this early stage. When Joining the team- I remember after lunchtime, sitting to meet the VP of business, and him asking me, “so who did you meet already?” …
According to one of the case studies done, the overall precision that the existing model provides is between 61–70%, with two main issues in its predictions:
These two factors caused the model results to present x2 higher risk factors to black defendants over whites.
The official algorithms for the ‘COMPAS’ solution are trade secrets,
But there are publications online that examine classifiers and linear regression models and come…
If you are working on AI/ML products, you probably already came across the words “precision” & “recall” along the way. These terms are being used to benchmark, optimize & improve our AI/ML products.
Precision and recall are numbers extracted by calculating the overall results of a given algorithm/ model.
This post will go over the key terminologies, list and explain the possible trade-offs between them through thoughts of the US justice system. Helping us as product people understand how and what we want to optimize. And for who are we doing it for?
Imagine you are now a prosecutor. In…
The Innocence Project has documented over 375 DNA exonerations in the United States; 21 of these cases served on death row, and with an average time served of 14 years before exoneration.
Approximately 25% of the wrongfully convicted confessed, and 11% pleaded guilty to a crime (later proven) they did not commit.
This can be hard to grasp for those of us encountering these numbers for the first time, But as hard as it is to believe, innocent people confess to crimes they did not commit even when their lives are on the line. …
Game of Thrones has broken so many records while presenting some of the most violent crimes in today’s television, spiced up with fantasy dragons.
If we look at the list of 2019 top10 best-rated TV shows by IMDB (with over 10K ratings), 5 out of 10 either have the official category of “crime” in their genre or portray criminal activity their main description. Those are just the ones where criminal aspects are explicitly described. That 50% easily represents the current interest in crime TV this past year.
Were we always obsessed with crime?
Our obsession with crime is not something…
Recently, I started working on a talk about data-storytelling. I was planning on creating a talk about data for non-data professionals, something that could break the barrier of data-dread — a common terror for many of my friends and colleagues who aren’t savvy with numbers.
Don’t get me wrong. It’s not like I have not experienced the proverbial data-dread myself. My early academic education was in fine arts with a minor in psychology, and I have started my product management career a direct path from being a UX professional.
Therefore, my relationship with data was gradually formed; this love affair…