October 16, 2024 at 12:00 am
Comments posted to this topic are about the item The Modern Algorithm of Chance
October 16, 2024 at 8:13 am
I worked on a product recommendation algorithm. For the most part if was a personalised sort order for results from a customer search. We recognised the danger of a self-fulfilling prophecy so 10% of the products from a search would be selected at random from the results beyond the 2nd page (people rarely go beyond page 2 of the results).
When we started the project it looked like a big data problem. 5 million customers and 250,000+ products and generating a scoring matrix between each customer and each characteristic for each product. However, we found that the attributes we had on 5 million customers produced 43 strongly cohesive clusters. When we looked at the product characteristics there were a lot that didn't exist in the real world. This collapsed the data down from trillions of records and terrabytes of data down to millions or records and low gigabytes of data.
The next logical product algorithm benefited from this collapse of data too. It became far easier to comprehend what the algorithm was doing and whether it was doing it as intended and to introduce a random element into it to avoid self fulfilling prophecies.
One area I think personalisation hasn't touched is the workplace. The debate on return to the office vs working from home is passionate. Some companies are adamant that people should return to the office as it was pre-COVID where the office was pretty much a one size fits all.
What is clear is that some people are on a spectrum with "suited to home working" being on one end and "suited to office only" being on the other. Could personalisation algorithms be used to affect the design of the workplace to make it more palatable? Can we match the work environment to the needs of personality traits? The goal being to design an office around what allows different groups of people to be productive?
October 16, 2024 at 2:09 pm
Many years ago I was reading a column by someone who was lamenting the change in her searches. She remembered searching for a term and the first few hits were relevant but then she would see other hits that would attract her attention and she was exposed to new items, thoughts, different things. But the algorithms now reduced all those random hits, or at least moved them several pages down. I was struck because it dawned on me that I had experienced the same thing. Sure, it lead down rabbit holes, and was a time suck when maybe you really needed information about your search term, but what an adventure. Things I had never heard of, options I wouldn't have thought of, oddities in the world, all sorts of things that might or might not catch my interest. Very similar to your analogy with the books.
October 16, 2024 at 2:48 pm
...
What is clear is that some people are on a spectrum with "suited to home working" being on one end and "suited to office only" being on the other. Could personalisation algorithms be used to affect the design of the workplace to make it more palatable? Can we match the work environment to the needs of personality traits? The goal being to design an office around what allows different groups of people to be productive?
Yes, though the concept of "fairness" and "equality" always causes issues here. Some places have done a merit thing, where people who do more or meet deadlines get more choices about WFH/WFO, though that requires a manager who can have hard conversations about why you can't WFH. Managerial skills are something we lack.
In terms of different types of office spaces, it might be the same thing. Usually higher performers get more closed offices, or quieter ones. How we manage that with those people when they don't really need quiet, or low/avg performers who do is likely more of a social problem than a design one.
October 16, 2024 at 3:38 pm
Many years ago I was reading a column by someone who was lamenting the change in her searches. She remembered searching for a term and the first few hits were relevant but then she would see other hits that would attract her attention and she was exposed to new items, thoughts, different things. But the algorithms now reduced all those random hits, or at least moved them several pages down. I was struck because it dawned on me that I had experienced the same thing. Sure, it lead down rabbit holes, and was a time suck when maybe you really needed information about your search term, but what an adventure. Things I had never heard of, options I wouldn't have thought of, oddities in the world, all sorts of things that might or might not catch my interest. Very similar to your analogy with the books.
Yep, I agree. I see more sponsored and targeted results, and less tangential things that might help me think differently. It's both something I appreciate and I wish were different.
October 16, 2024 at 4:58 pm
In terms of different types of office spaces, it might be the same thing. Usually higher performers get more closed offices, or quieter ones. How we manage that with those people when they don't really need quiet, or low/avg performers who do is likely more of a social problem than a design one.
The tricky bit is working out what someone's optimal sustainable performance actually is and whether their environment aids or prevents them achieving that level. Then there is what constitutes reasonable accommodation of needs. I'm a bit wary of a productive environment being seen as a reward. "Work hard and we will get you a monitor bigger than 14" and an unbroken chair" doesn't work for me.
Having seen many environments over the years, what makes a productive environment is a complex thing. Looking back on my career I think the most productive environments weren't those with the beanbags and foozball tables, they were those where the managers knew their staff's strengths/weaknesses, what would cause stress and when that might be necessary.
Somehow a drab office can be energising when the right people are in it, but thank God the days where those awful drinks machines that dispensed a cup of brown are long gone.
October 22, 2024 at 10:14 pm
People make or break many things.
Viewing 7 posts - 1 through 6 (of 6 total)
You must be logged in to reply to this topic. Login to reply