Use information and prediction to reduce disorderly parking

Last registered on July 13, 2021
View Trial History

Pre-Trial

Trial Information

General Information

Title
Use information and prediction to reduce disorderly parking
RCT ID
AEARCTR-0007952
Initial registration date
July 12, 2021

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
July 13, 2021, 9:38 AM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

Country
China
Region
Nanjing

Primary Investigator

Name
Zilin Zhan
Affiliation
Beijing Jiaotong University
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Yacan Wang
PI Affiliation
Department of Economics, School of Economics and Management Beijing Jiaotong University Beijing 100044, China
Contact Investigator
PI Name
Zilin Zhan
PI Affiliation
Department of Economics, School of Economics and Management Beijing Jiaotong University Beijing 100044, China
Contact Investigator
PI Name
Duan Su
PI Affiliation
Department of Economics, School of Economics and Management Beijing Jiaotong University Beijing 100044, China
Contact Investigator
PI Name
Nan Yang
PI Affiliation
Graduate School of Economics, University of Tokyo, Tokyo, Japan
Contact Investigator
PI Name
Haoran He
PI Affiliation
Department of Economics Business School, Beijing Normal University Beijing 100875, China
Contact Investigator

Additional Trial Information

Status
On going
Start date
2021-04-28
End date
2021-10-28
Keywords
Behavior
Additional Keywords
Behavior, Transportation, Bike-sharing, Machine Learning, Precision Intervention
JEL code(s)
Public economics, Transportation economics
Secondary IDs
National Natural Science Foundation of China and the Joint Programming Initiative Urban Europe, National Natural Science Foundation of China
Abstract
Dockless bike-sharing is popular and provides the commuting service for "the last mile of trip". Users often make improper parking and influence the public environment and bicycle circularity. Even some parking locations are already very crowded, users still park shared bicycles here. The company needs to take manpower to carry these bicycles. In our experiment, we use machine learning to predict the destination of users' trips. If users will ride to very busy areas, we send information through app to remind them to avoid parking bicycles here.
External Link(s)

Registration Citation

Citation
He, Haoran et al. 2021. "Use information and prediction to reduce disorderly parking." AEA RCT Registry. July 13. https://doi.org/10.1257/rct.7952-1.0
Sponsors & Partners

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information
Experimental Details

Interventions

Intervention(s)
Reminder: Use app information to remind users to reduce parking in crowded areas.
Social norm information: Use app information to emphasize the proportion of users who parking orderly.
Altruism information: Use app information to emphasize the positive externality that parking orderly.
Social norm and altruism information: Use app information to emphasize the proportion of users who parking orderly and the positive externality that parking orderly.
Intervention Start Date
2021-06-28
Intervention End Date
2021-08-28

Primary Outcomes

Primary Outcomes (end points)
Whether to park bicycles in crowded areas
Primary Outcomes (explanation)
orderly parking

Secondary Outcomes

Secondary Outcomes (end points)
None
Secondary Outcomes (explanation)
None

Experimental Design

Experimental Design
During treatment period, when a subject unlock a shared bicycle mobile, the company will predict the destination of his or her riding. If we forecast that the subject will ride to a very crowded area, the app sends treatment information to them.
Experimental Design Details
Users are assigned to control or treatment group randomly. During treatment period, for each trip, we use the machine learning algorithm to predict the user's destination when she scans QRs based on the lock point corresponding to her historical lock point. If the user is forecasted to ride to the crowded area, the app will show the treatment information to her.
Randomization Method
Completed randomization
Randomization Unit
times
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
One city
Sample size: planned number of observations
Expected over 5000 bike-sharing users
Sample size (or number of clusters) by treatment arms
1000 users for control, 1000 users for reminder group, 1000 users for social norm group, 1000 users for altruism group, 1000 users for Social norm and altruism group.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Standard deviation: 20% Percentage: 13% behavioral shift Minimum effect size: 930 of each experimental group, a total of 5580 subjects are needed.
Supporting Documents and Materials
IRB

Institutional Review Boards (IRBs)

IRB Name
IRB Approval Date
IRB Approval Number
Analysis Plan

Post-Trial

Post Trial Information

Study Withdrawal

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Intervention

Is the intervention completed?
No
Data Collection Complete
Data Publication

Data Publication

Is public data available?
No

Program Files

Program Files
Reports, Papers & Other Materials

Relevant Paper(s)

Reports & Other Materials