Human-AI Interaction: Human Behavior Routineness Shapes AI Performance

<p>These are codes for the <em>routineness </em>model and its corresponding data, plus a subset of the anonymized and processed data for the prediction models containing 10.000 users.</p> <ul> <li>Data</li> </ul> <ol> <li>dataset.tar.gz &mdash; Data for the <em>routineness</em> model, including 151 .parquet files, each of them&nbsp;containing 1,000 anonymized users&#39; hourly behavioural observations.</li> <li>subset_train.csv&nbsp;&mdash; A subset of the mobility data for training on prediction models, containing 10,000 anonymized users.</li> <li>subset_test.csv&nbsp;&mdash; A subset of the mobility data for testing,&nbsp;containing the same 10,000 anonymized users.</li> </ol> <ul> <li>Code</li> </ul> <ol> <li>routineness.stan &mdash; A Stan program, that allowed us to measure the weight of the routine/random behaviours of&nbsp;each individual and to calculate their <em>routineness</em>.</li> <li>run.py &mdash; A Python file to run the Stan program. Noted that a package, CmdStanPy, must be installed.&nbsp;Under the hood, CmdStanPy uses the CmdStan command line interface to compile and run a Stan program.</li> </ol>