Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
CityGravity
Search
Nikita Kirnosov
October 12, 2015
130
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
CityGravity
Nikita Kirnosov
October 12, 2015
Featured
See All Featured
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
630
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
3.1k
Being A Developer After 40
akosma
92
590k
The Organizational Zoo: Understanding Human Behavior Agility Through Metaphoric Constructive Conversations (based on the works of Arthur Shelley, Ph.D)
kimpetersen
PRO
0
500
Designing Powerful Visuals for Engaging Learning
tmiket
1
610
Leading Effective Engineering Teams in the AI Era
addyosmani
9
2.7k
Building Flexible Design Systems
yeseniaperezcruz
330
41k
Learning to Love Humans: Emotional Interface Design
aarron
275
41k
Efficient Content Optimization with Google Search Console & Apps Script
katarinadahlin
PRO
1
930
Fireside Chat
paigeccino
43
4.1k
Everyday Curiosity
cassininazir
0
350
The Cult of Friendly URLs
andyhume
79
7k
Transcript
CityGravity Nikita Kirnosov Get to know
a city
How do tourists make plans? 1. Decide what
interests them. 2. Book a nice hotel What’s missing? OpBmal accommodaBon allows you to spend minimum Bme traveling to interesBng stuff
Find a center of gravity and stay close to
it! Let’s do it! TransportaBon Bmes AIracBons I’ll see
Does it sound right?
Does it sound right?
Model & Improve clustering + ranking
How to opBmally group the aIracBons? Not realisBc:
you do not go to hotel aPer each aIracBon Not achievable: ~ 1,000,000 Google API calls for California
Calculate the distance matrix and apply
DBSCAN clustering. Density condiBon: distance < 1 mi The cluster is too big… How to opBmally group the aIracBons?
Apply hierarchical clustering to the big cluster to
achieve subcluster diameter < 2 mi ~ 40,000 Google API calls for California How to opBmally group the aIracBons?
Solved!
Looking for the unique locaBon: accurate result
Me, Nikita
Me, Nikita
What are we looking for? Get further –
ride longer I am the middle, how do I get out? Total (Travel 1me * Number of objects)
My Data