Forecasting Parking Availability for Providing Value-Added Services to Customers of Parking Lots

Project Details


Fall 2016


Aylada Khunvaranont, Ching-Yu Li, Tsun-Hsien Tang, Tzu-Hsin Hsieh, Wan-Yi Chou





Business Problem

Taiwan is considered as a small island comparing to her population. Besides, with high population density in the city area such as in Taipei city, New Taipei city, it is quite difficult to find an available parking space in those places. Therefore, we want to propose a mobile application that can provide parking lot information to customer with value-added services such as the availability of the parking lot and information about how long the customer needs to wait if the parking lot is full. With our proposed mobile application, the customer can plan their schedule in advance which can increase their satisfaction in using the facility. Moreover, with the forecasting approximate waiting time, the customer will be prepared for waiting which can help lower their frustration. Additionally, the parking lot company can better manage their parking lots via the user log in the mobile application.


We have acquired data from one of the Taiwanese parking lot company. The primary data set we used is mainly a collection of timestamp of going in and coming out cars from the parking lots. In addition, we also have secondary data set such as of forecasted weather, department store holiday promotion period, forecasting number of airport passengers (ridership). The data we used for analysis is in two months period time (2016/3-2016/4) as a proof of concept to our project.

Forecasting Solution

To begin with, we explored the data and chose six parking lots based on their use. In addition, basically, the time series of those parking lots has no trend but seasonality. Then we have tried many forecasting models in order to obtain the most suitable output for our value-added services. We have provided the outcomes with point values and in range of forecasted values. In terms of the performance, our models can capture the pattern of each different type of parking lots and provide a useful forecasting. For more information, please refer to the detailed report below.


We would like to suggest that the company should collect the user data in terms of whether or not the customers that submit the queries actually use the facility as a way to measure the usability of the application. Since we are forecasting the availability of the parking lots in every five minutes interval for a week in advance which takes a great computational power, we would like to recommend that the company should have computers that are powerful enough.

Application Area: