UNLOCKING HIDDEN DEMAND: UTILIZING COMPUTER VISION FOR STREET HAILING OPTIMIZATION IN BLUE BIRD TAXI
Despite the technology disruption from online ride-hailing, street-hailing is still popular in among certain people in Jakarta, the capital city of Indonesia. The taxi firms still count street hailing as a highly reliable service that offers unique benefits to both passengers and drivers as opposed...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Subjects: | |
| Online Access: | https://digilib.itb.ac.id/gdl/view/85621 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Despite the technology disruption from online ride-hailing, street-hailing is still popular in among certain people in Jakarta, the capital city of Indonesia. The taxi firms still count street hailing as a highly reliable service that offers unique benefits to both passengers and drivers as opposed to the online services. The easy experience and swift decision of hailing a taxi have a sense of immediacy that cannot be replicated by online apps. However, the classic street hailing service faces a few challenges, especially for Blue Bird as one of the taxi operators in Jakarta. Unlike ride hailing apps where demand is recorded digitally, street hailing is often lack of visibility into street demand, leading to fleet operation inefficiency. This is where Computer Vision (CV) technology offers an innovative approach to improve visibility and identify the unmet demand for street-hailing, by capturing the gestures of people hailing a taxi from the street and count it as a demand for future analysis.
Prior to its implementation, it is important to assess the potential business impact of deploying this digital innovation. This research aims to identify the potential street-hailing demand that is currently hidden, estimating the additional demand that might be absorbed after the CV deployment. The research applies a mixed method approach, combining quantitative and qualitative methods. The quantitative one highlights an inference analysis to estimate potential demand that were previously not recorded. The qualitative method aims to validate and complement the findings from the quantitative method. The insights are also valuable for crafting a high-level design of street-hailing detection system, shaping overall architecture and functionality of the system to address practical considerations effectively. All these preliminary analyses will contribute to Blue Bird to serve as a foundation for a strategic planning of the CV system for street hailing detection.
|
|---|