Drawing business conclusions
In this section, we'll formulate some final considerations using the results that we got from applying our ML model.
By enriching the previous query with a parent SELECT COUNT
statement, we can identify how many predictions are less than 15
minutes away from the actual value.
Let's execute the following query to calculate how often the trip duration predictions are far from the actual values:
SELECT COUNT (*) FROM ( SELECT tripduration as actual_duration, predicted_label as predicted_duration, ABS(tripduration - predicted_label) difference_in_min FROM ML.PREDICT(MODEL `04_nyc_bike_sharing.trip_duration_by_stations_and_day`, ( SELECT start_station_name, end_station_name, ...