Главная
Study mode:
on
1
Introduction
2
Why are AI Machine Learning and Data Science still out of reach
3
What does it mean to move beyond giving your data scientists access
4
Salesforces approach to AI
5
Agenda
6
Building ML apps
7
No company is building one app
8
We need a third data scientist
9
Different degrees of skill set
10
Different data sizes
11
Classification
12
Language
13
Customization
14
Trust
15
Fixing leaks
16
Traditional AI process
17
Automation
18
Data Science Journey
19
Building Models
20
Getting Access to Data
21
Shipping Your App
22
Everyone Needs a Data Scientist
23
Data Scientists and Software Developers
24
Data Scientist
25
Building a Platform
26
Working Together
27
Finding opportunities for reuse
28
Transmogrify
29
Automated Pipeline
30
Data Sampling
31
Text Data
32
Stop Words
33
Learning Opportunities
34
Model Selection
35
The Job is Never Done
36
Metrics to Drive Agility
37
What Happens After Deployment
38
Minimum Viable Product
39
Agile Process
40
Agile Data Science
41
Monitoring
42
Model Monitoring
43
Investigate
44
Backlog
45
Focus
46
Key takeaways
47
Join the open source community
48
Thank you
49
Getting started in data science
50
ACM resources
51
Open source components
52
Platform secured experimentation
53
Latency considerations
Description:
Explore the intricacies of implementing large-scale machine learning in production with Sarah Aerni, Director of Data Science at Salesforce Einstein, in this insightful conference talk. Discover how Salesforce successfully integrates Agile methodologies into data science practices to serve over 100,000 customers. Learn about the company's innovative platform, including the open-source autoML library TransmogrifAI, and gain valuable insights into experimentation, deployment, and monitoring processes. Delve into the challenges of providing data scientists with effective tools for model deployment and continuous iteration. Understand the importance of rapid iteration, automated model retraining, and shipping billions of predictions daily. Explore strategies for detecting issues, identifying improvement opportunities, and maintaining a data science backlog through alerting and monitoring systems. Gain practical knowledge on fostering data science innovation within an Agile framework and learn from Salesforce's experiences in scaling AI applications across a vast customer base. Read more

Agile Data Science - Achieving Salesforce-Scale Machine Learning in Production

Association for Computing Machinery (ACM)
Add to list