{"id":270,"date":"2021-04-25T17:05:46","date_gmt":"2021-04-25T17:05:46","guid":{"rendered":"https:\/\/www.lancaster.ac.uk\/stor-i-student-sites\/ziyang-yang\/?p=270"},"modified":"2021-04-29T22:38:26","modified_gmt":"2021-04-29T22:38:26","slug":"handling-human-stubbornness-when-people-think-they-are-smarter-than-data-science","status":"publish","type":"post","link":"https:\/\/www.lancaster.ac.uk\/stor-i-student-sites\/ziyang-yang\/2021\/04\/25\/handling-human-stubbornness-when-people-think-they-are-smarter-than-data-science\/","title":{"rendered":"Handling human stubbornness when people think they are smarter than data science!"},"content":{"rendered":"\n

Last month, we had a problem-solving day talking about handling human stubbornness during the implementation of data science. You may hear data science could make good decisions, like data science help groceries to make a better decision<\/a>. And you may be also familiar with the travel route planned by Google map! Like us, delivery companies also plan an optimized route for drivers. For example, drivers for delivery companies (e.g.\u00a0Amazon) have to\u00a0deliver hundreds of parcels to many different addresses every\u00a0day. And these companies use vehicle routing models to compute the best\u00a0routes for delivery drivers (maybe the routes has the least time). <\/p>\n\n\n\n

\"\"
At left is a delivery route computed by the Last Mile team\u2019s optimization software, at right the route that a delivery driver actually chose to drive. (Map details have been omitted.) Green symbols (A and B)<\/em> indicate the driver\u2019s starting locations, purple symbols (also A and B)<\/em> the ending locations. – cited from Amazon<\/figcaption><\/figure><\/div>\n\n\n\n

However, usually, drivers deviate from the optimised delivery route computed by data science to reduce the journey time. This is because usually, they think they are more familiar with this area and have their own driving habits. Unfortunately, most time, they increase the time required to\u00a0unload packages from the van at stops. <\/p>\n\n\n\n

\"Stubbornness<\/figure><\/div>\n\n\n\n

Data scientists always consider how accurate their model is but paying less consideration to monitor the implementation of the whole process. However, make sure the whole process as the plan is much harder than designing an efficient algorithm. Recently, Amazon and MIT hold a new competition<\/a>, that they want to find a solution that reducing the probability of drivers’ deviation. <\/p>\n\n\n\n

Our group discussed this problem and considered 2 possible ways to help improve the drivers’ loyalty:<\/p>\n\n\n\n

Specific personalised driver routes<\/strong><\/h3>\n\n\n\n

Most drivers are deviating from the route plan since they have their own driving habits. So, why not design an optimised route combined with their driving habits? <\/p>\n\n\n\n

\"Skoda<\/figure><\/div>\n\n\n\n

We could collect information:<\/p>\n\n\n\n