Thread by @sciencebanshee

There was an NBC article this morning about women in STEM being underestimated by male colleagues, and am coping by being OBNOXIOUSLY CONFIDENT. LET'S DO SOME VERY IMPORTANT SCIENCE, TWITTER.
#WomenInSTEM #WomenWhoCode

I took a class this semester on computational models of human decision making, and it was awesome. I learned about algorithms, and how information is taken in and updated to help us decide *stuff*

The final project was to develop code that could produce data and learn from itself (given parameters I set...the computers aren't going to kill us all.)
(Yet.)

I would happily outsource most, if not all, of my decisions to computers (for more on this, ask me about my 'death-cursed murder house' index from the last time we moved. Relatedly, my spouse's 'spousal angst' index) and wanted to see if I could train a model to predict me.

I wanted a behaviour that was habitual, where the choices had stable values and where I choose to exploit familiarity rather than explore new options.

For example, think about going to a bakery. They have your favourite thing, but you make a killer that thing. Do you try theirs, or do you try that other thing? I wanted to eliminate as much of this guesswork as possible.

(Side poll, what do you order at the bakery?)

I also wanted something that occurred regularly. So I went with tea. I collected my tea choices at three time points over a two-week period and used this as training data:

Each tea/tea refusal (n=6) was coded with a value of 1 every time I selected it, and I tried to train my Tea Bot to recommend my next choice after studying the training data I gave it (a six-armed bandit for the nerds).

With only 42 data points (3 choices per day * 14 days), performance was poor, and it vacillated between random selection and defaulting to Yorkshire tea (the most popular) depending on the parameters I gave it with an average accuracy of 8%. This was sub-optimal.

Looking at the data, I (and perhaps you!) can see a clear pattern. In the mornings, I drink an unflavoured black tea. In the afternoons, I'm a little more adventurous, and in the evenings, what I drink depends on whether or not I have to get up early the next day.

I decided to add day and time as context parameters to my Tea Bot. I also made it interactive, because I think making computers talk is hilarious.

Once the Tea Bot knows what day and time it is, it selects the relevant cases from the training dataset and calculates the probability of me selecting each of the six options based on what I did at the same day/time in the past.

It selects the tea with the highest probability and recommends that (this is a greedy policy - it always goes for the highest value rather than trying something new for funsies). If multiple teas are tied, it randomly selects one and offers it.

I can either accept its recommendation, or refuse and choose something else. In either case, the Tea Bot adds a new row to the training dataset that records the day, time, and my choice. It can then use this choice in the future.

I recorded my tea consumption for an additional ten days, and tested the Tea Bot's accuracy after I made my decisions (this cuts down on suggestibility).

It was 76.7% accurate. This is amazing. And also hilarious.

But is it useful?

If you're reading this on the internet (rather than my hand-lettered periodical), you're part of a much more sophisticated version of this bot that takes your searches, clicks, likes, etc. and tries to anticipate what you're going to do next based on what you already did.

So where does the Tea Bot fit in? In healthcare, wearables (things that track an individual's data. Think heart rate blood sugar, etc) are growing in popularity. These track biomarkers and compare the participant to population norms, or norms based on that individual's past data.

These tools track your automatic responses and can prompt you to take/avoid an action, but what about habitual behaviours, like hobbies (or tea drinking)?

My background is in Alzheimer's disease (AD), and keeping mentally active is super important. Unfortunately, individuals with AD often present with a lack of motivation or an inability to "get going" with previously enjoyed activities.

Something like the Tea Bot could be used to recommend activities based on the individual's history. They, or someone who knows them well, could provide a typical schedule, which could provide the training data for a simple bot.

Something like this probably also exists, and I know that people can do this, but we live in the future, dammit. The point is to make friends and show how amusing coding projects can be used in everyday life.

So thanks for stopping by! The kettle is on, and you're welcome to a cup.