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
Safe Dining Talk
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
ahmad0510
February 17, 2016
Technology
0
34
Safe Dining Talk
Recommender for safe eating places in your neighborhood
ahmad0510
February 17, 2016
Tweet
Share
More Decks by ahmad0510
See All by ahmad0510
Safe Dining Talk
ahmad0510
0
49
Safe Dining
ahmad0510
1
33
Safe Dining
ahmad0510
0
40
Safe Dining
ahmad0510
0
44
Safe Dining
ahmad0510
0
44
Safe Dining
ahmad0510
1
40
SafeDining
ahmad0510
0
48
SafeDining2
ahmad0510
0
33
Safedining3
ahmad0510
0
41
Other Decks in Technology
See All in Technology
AIエージェントを開発しよう!-AgentCore活用の勘所-
yukiogawa
0
160
学生・新卒・ジュニアから目指すSRE
hiroyaonoe
2
600
ファインディの横断SREがTakumi byGMOと取り組む、セキュリティと開発スピードの両立
rvirus0817
1
1.3k
30万人の同時アクセスに耐えたい!新サービスの盤石なリリースを支える負荷試験 / SRE Kaigi 2026
genda
4
1.3k
SREが向き合う大規模リアーキテクチャ 〜信頼性とアジリティの両立〜
zepprix
0
450
What happened to RubyGems and what can we learn?
mikemcquaid
0
300
CDKで始めるTypeScript開発のススメ
tsukuboshi
1
400
日本の85%が使う公共SaaSは、どう育ったのか
taketakekaho
1
150
[CV勉強会@関東 World Model 読み会] Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models (Mousakhan+, NeurIPS 2025)
abemii
0
130
【Oracle Cloud ウェビナー】[Oracle AI Database + AWS] Oracle Database@AWSで広がるクラウドの新たな選択肢とAI時代のデータ戦略
oracle4engineer
PRO
2
140
Tebiki Engineering Team Deck
tebiki
0
24k
Kiro IDEのドキュメントを全部読んだので地味だけどちょっと嬉しい機能を紹介する
khmoryz
0
190
Featured
See All Featured
Building an army of robots
kneath
306
46k
sira's awesome portfolio website redesign presentation
elsirapls
0
150
Become a Pro
speakerdeck
PRO
31
5.8k
Done Done
chrislema
186
16k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
1.7k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
GitHub's CSS Performance
jonrohan
1032
470k
Building AI with AI
inesmontani
PRO
1
690
Building Adaptive Systems
keathley
44
2.9k
Money Talks: Using Revenue to Get Sh*t Done
nikkihalliwell
0
150
Have SEOs Ruined the Internet? - User Awareness of SEO in 2025
akashhashmi
0
270
End of SEO as We Know It (SMX Advanced Version)
ipullrank
3
3.9k
Transcript
Ahmad Haider Insight Data Science 2016
Personal Story What if I could find which restaurants are
safe and which are not? Mugged @Parking lot ! L Hungry for Pizza! Closest pizza location
Makes Real-Time Recommendations for Safety Ratings Restaurants in a Neighborhood
SafeDining app
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location Under the hood…
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location p1 p2 p3 p4 p5 p1 p2 p3 p4 p1 p2 p1 p2 p3 p4 p5 p6 p7 p8 p1 Crime Location Crime Probability
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location p1 p2 p3 p4 p5 p1 p2 p3 p4 p1 p2 p1 p2 p3 p4 p5 p6 p7 p8 p1 Crime Location Crime Probability 1. pRest 1. pRest 1. pRest 1. pRest pRest Crime Probability at restaurant
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location p1 p2 p3 p4 p5 p1 p2 p3 p4 p1 p2 p1 p2 p3 p4 p5 p6 p7 p8 p1 Crime Location Crime Probability 1. pRest 1. pRest 1. pRest 1. pRest pRest Crime Probability at restaurant pRest pRest pRest pRest pRest pRest pRest
I want to eat Pizza at 2+ rated restaurant within
3 miles of my location p1 p2 p3 p4 p5 p1 p2 p3 p4 p1 p2 p1 p2 p3 p4 p5 p6 p7 p8 p1 Crime Location Crime Probability 1. pRest 1. pRest 1. pRest 1. pRest pRest Crime Probability at restaurant pRest pRest pRest pRest pRest pRest pRest 2. Relative Safety Index 2. Relative Safety Index 2. Relative Safety Index 2. Relative Safety Index
Workflow Crime dataset Yelp API Preprocessing + Cleaning Defining classification
problem Feature Engineering Choosing a model Validation 10-fold cross validation Cross entropy loss measure
Multiclass Classification Predict the probability of crime at any
hour at any given location Features: 35 -- Location (Lat., Long. etc.) , Time (dd, wk, mm, yyyy) Labels: 24 classes (hour of day) Logistic Regression Cross entropy loss measure = 2.95 Algorithm
Theft Residential Burglary Robbery Assault Source: mylocalcrime.com Validation My analysis
mylocalcrime.com
• Ahmad Haider • PhD thesis: “Measurement of energy landscapes
of biological interactions using Boltzmann sampling” • Georgia Tech • Love hiking About Me
None