Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.
Recruiting Solutions 
1 
My Three Ex’s: 
A Data Science Approach for 
Applied Machine Learning
Dedicated to 3 of my favorite ex co-workers.
First, a disclosure. 
This isn’t a talk about machine learning. 
It’s a talk about applying machine learning. 
What’s the ...
Let’s talk about something else for a moment. 
Hash Tables 
4
What you (need to) know about hash tables. 
Theory Application 
5 
Class HashMap<K,V> 
java.lang.Object 
java.util.Abstrac...
Now let’s get back to machine learning! 
6
Please allow me to introduce my three ex’s. 
Express. 
Explain. 
Experiment. 
7
Embrace the data science mindset. 
Express 
Understand your utility and inputs. 
Explain 
Understand your models and metri...
Express. 
9
How to train your machine learning model. 
1. Define your objective function. 
2. Collect training data. 
3. Build models....
You can only improve what you measure. 
11 
Clicks? 
Actions? 
Outcomes?
Be careful how you define precision… 
12
Account for non-uniform inputs and costs. 
13
Stratified sampling is your friend. 
14
An example of segmenting models. 
15 
Searcher: Recruiter 
Query: Person Name 
Searcher: Job Seeker 
Query: Person Name 
S...
Express yourself in your feature vectors. 
16
Express: Summary. 
 Choose an objective function that models utility. 
 Be careful how you define precision. 
 Account ...
Explain. 
18
With apologies to the little prince. 
19
Everyone is talking about Deep Learning. 
20
But accuracy isn’t everything. 
21
Explainable models, explainable features. 
 Less is more when it comes to explainability. 
 Algorithms can protect you f...
Linear regression? Decision trees? 
 Linear regression and decision trees favor explainability 
over accuracy, compared t...
Explain: Summary. 
 Accuracy isn’t everything. 
 Less is more when it comes to explainability. 
 Don’t knock linear mod...
Experiment. 
25
Why experiments matter. 
“You have to kiss a lot of frogs to find one prince. 
So how can you find your prince faster? 
By...
Life in the age of big data. 
Yesterday Today 
27 
Experiments are expensive, 
choose hypotheses wisely. 
Experiments are ...
So should we just test everything? 
28
Optimize for the speed of learning. 
29 
vs
Be disciplined: test one variable at a time. 
• Autocomplete 
• Entity Tagging 
• Vertical Intent 
• # of Suggestions 
• S...
Experiment: Summary. 
 Kiss lots of frogs: experiments are cheap. 
 But test in good faith – don’t just flip coins. 
 O...
Bringing it all together. 
Express 
Understand your utility and inputs. 
Explain 
Understand your models and metrics. 
Exp...
33 
Daniel Tunkelang 
dtunkelang@linkedin.com 
https://linkedin.com/in/dtunkelang
Próxima SlideShare
Cargando en…5
×

My Three Ex’s: A Data Science Approach for Applied Machine Learning

11.401 visualizaciones

Publicado el

My Three Ex’s: A Data Science Approach for Applied Machine Learning
Daniel Tunkelang (LinkedIn)

Presented at QCon San Francisco 2014 in the Applied Machine Learning and Data Science track
https://qconsf.com/presentation/my-three-ex%E2%80%99s-data-science-approach-applied-machine-learning

Abstract

This talk is about applying machine learning to solve problems.

It’s not a talk about machine learning — or at least not about the theory of machine learning. Theoretical machine learning requires a deep understanding of computer science and statistics. It’s one of the most studied areas of computer science, and advances in theoretical machine learning give us hope of solving the world’s “AI-hard” problems.

Applied machine learning is more grounded but no less important. We are surrounded by opportunities to apply classifiers, learn rules, compute similarity, and assemble clusters. We don’t need to develop new algorithms for any of these problems — our textbooks and open-source libraries have done that hard work for us.

But algorithms are not enough. Applying machine learning to solve problems requires a data science mindset that transcends the algorithmic details.

In this talk, I’ll communicate the data science mindset by describing my three ex’s: express, explain, and experiment. These three activities are the pillars of a successful strategy for applying machine learning to solve problems. Whether you’re a machine learning novice or expert, I hope you’ll leave this talk with some practical wisdom you can apply to your next project.

Publicado en: Tecnología
  • Are You Heartbroken? Don't be upset, let Justin help you get your Ex back. ▲▲▲ http://ow.ly/mOLD301xGxr
       Responder 
    ¿Estás seguro?    No
    Tu mensaje aparecerá aquí

My Three Ex’s: A Data Science Approach for Applied Machine Learning

  1. Recruiting Solutions 1 My Three Ex’s: A Data Science Approach for Applied Machine Learning
  2. Dedicated to 3 of my favorite ex co-workers.
  3. First, a disclosure. This isn’t a talk about machine learning. It’s a talk about applying machine learning. What’s the difference? 3
  4. Let’s talk about something else for a moment. Hash Tables 4
  5. What you (need to) know about hash tables. Theory Application 5 Class HashMap<K,V> java.lang.Object java.util.AbstractMap<K,V> java.util.HashMap<K,V> Type Parameters: K - the type of keys maintained by this map V - the type of mapped values All Implemented Interfaces: Serializable, Cloneable, Map<K,V>
  6. Now let’s get back to machine learning! 6
  7. Please allow me to introduce my three ex’s. Express. Explain. Experiment. 7
  8. Embrace the data science mindset. Express Understand your utility and inputs. Explain Understand your models and metrics. Experiment Optimize for the speed of learning. 8
  9. Express. 9
  10. How to train your machine learning model. 1. Define your objective function. 2. Collect training data. 3. Build models. 4. Profit! 10
  11. You can only improve what you measure. 11 Clicks? Actions? Outcomes?
  12. Be careful how you define precision… 12
  13. Account for non-uniform inputs and costs. 13
  14. Stratified sampling is your friend. 14
  15. An example of segmenting models. 15 Searcher: Recruiter Query: Person Name Searcher: Job Seeker Query: Person Name Searcher: Recruiter Query: Job Title Searcher: Job Seeker Query: Job Title
  16. Express yourself in your feature vectors. 16
  17. Express: Summary.  Choose an objective function that models utility.  Be careful how you define precision.  Account for non-uniform inputs and costs.  Stratified sampling is your friend.  Express yourself in your feature vectors. 17
  18. Explain. 18
  19. With apologies to the little prince. 19
  20. Everyone is talking about Deep Learning. 20
  21. But accuracy isn’t everything. 21
  22. Explainable models, explainable features.  Less is more when it comes to explainability.  Algorithms can protect you from overfitting, but they can’t protect you from the biases you introduce.  Introspection into your models and features makes it easier for you and others to debug them.  Especially if you don’t completely trust your objective function or the representativeness of your training data. 22
  23. Linear regression? Decision trees?  Linear regression and decision trees favor explainability over accuracy, compared to more sophisticated models.  But size matters. If you have too many features or too deep a decision tree, you lose explainability.  You can always upgrade to a more sophisticated model when you trust your objective function and training data.  Build a machine learning model is an iterative process. Optimize for the speed of your own learning. 23
  24. Explain: Summary.  Accuracy isn’t everything.  Less is more when it comes to explainability.  Don’t knock linear models and decision trees!  Start with simple models, then upgrade. 24
  25. Experiment. 25
  26. Why experiments matter. “You have to kiss a lot of frogs to find one prince. So how can you find your prince faster? By finding more frogs and kissing them faster and faster.” -- Mike Moran 26
  27. Life in the age of big data. Yesterday Today 27 Experiments are expensive, choose hypotheses wisely. Experiments are cheap, do as many as you can!
  28. So should we just test everything? 28
  29. Optimize for the speed of learning. 29 vs
  30. Be disciplined: test one variable at a time. • Autocomplete • Entity Tagging • Vertical Intent • # of Suggestions • Suggestion Order • Language • Query Construction • Ranking Model 30
  31. Experiment: Summary.  Kiss lots of frogs: experiments are cheap.  But test in good faith – don’t just flip coins.  Optimize for the speed of learning.  Be disciplined: test one variable at a time. 31
  32. Bringing it all together. Express Understand your utility and inputs. Explain Understand your models and metrics. Experiment Optimize for the speed of learning. 32
  33. 33 Daniel Tunkelang dtunkelang@linkedin.com https://linkedin.com/in/dtunkelang

×