Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Predicting YouBike
Search
brandon liu
May 28, 2015
Research
0
98
Predicting YouBike
Modeling demand for Taipei area bike share stations
brandon liu
May 28, 2015
Tweet
Share
More Decks by brandon liu
See All by brandon liu
OpenStreetMap in Architecture and Planning
bdon
0
860
Other Decks in Research
See All in Research
ロボット学習における大規模検索技術の展開と応用
denkiwakame
1
140
Combinatorial Search with Generators
kei18
0
1k
機械学習と数理最適化の融合 (MOAI) による革新
mickey_kubo
1
400
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
1.1k
20250725-bet-ai-day
cipepser
2
500
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
190
スキマバイトサービスにおける現場起点でのデザインアプローチ
yoshioshingyouji
0
250
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
kurita
1
280
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
230
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
satai
3
390
When Learned Data Structures Meet Computer Vision
matsui_528
1
130
Integrating Static Optimization and Dynamic Nature in JavaScript (GPCE 2025)
tadd
0
110
Featured
See All Featured
XXLCSS - How to scale CSS and keep your sanity
sugarenia
249
1.3M
Java REST API Framework Comparison - PWX 2021
mraible
34
8.9k
For a Future-Friendly Web
brad_frost
180
10k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
2
76
Designing Experiences People Love
moore
142
24k
KATA
mclloyd
PRO
32
15k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
55
3k
Speed Design
sergeychernyshev
32
1.2k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.7k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.1k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
15k
Transcript
Predicting YouBike YouBike 預測 youbikeforecast.com 劉知岳 (Brandon)
[email protected]
Why Forecast?
UNDERSTAND Observe past phenomena confirm or deny intuitions based on
data quantify service quality
MAKE DECISIONS See what is likely to happen in the
immediate future
What applications? http://pureinformation.net/transit-tracker/
None
Public YouBike API http://opendata.dot.taipei.gov.tw/opendata/ gwjs_cityhall.json
youbikeforecast.com
TOOLS LevelDB - data store Go, nginx, python, EC2 -
server Leaflet, d3 - web page
The shape of the data tells a story
How might we classify YouBike stations based on usage patterns?
Pattern: Morning/Evening Commute (信義/杭州路⼝口)
Pattern: Night Owls (國⽗父紀念堂)
Pattern: School (公館(台⼤大前⾯面)
Choosing a metric What can we measure that affects users?
How many minutes per day you can’t rent a bike (or what % of the day)
Pricing change March 2015(師⼤大)8% Unavailable
Pricing change April 2015(師⼤大)3% Unavailable
Improve the model? Weekend/Weekday (信義/杭州)
Improve the model? Weather (師⼤大) 下⼤大⾬雨
Adjustments
github.com/bdon/youbike-data