Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Machine Learning for Digital Advertising Marc Garcia Outreach digital - June 14th, 2016 1 / 50 Machine Learning for Digita...
Digital advertising: a data scientist point of view 2 / 50 Machine Learning for Digital Advertising - @datapythonista - @o...
Digital advertising: a data scientist point of view What is the Internet? A lot of bored people... 3 / 50 Machine Learning...
Digital advertising: a data scientist point of view ...who use a gadget... 4 / 50 Machine Learning for Digital Advertising...
Digital advertising: a data scientist point of view ...to access useless sites. 5 / 50 Machine Learning for Digital Advert...
Digital advertising: a data scientist point of view Ok, some of them are looking for something. 6 / 50 Machine Learning fo...
What is our goal? 7 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
What is our goal? Get their money! 8 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
What is our goal? That’s the truth, but let’s say it in a more subtle way... 9 / 50 Machine Learning for Digital Advertisi...
What is our goal? We want to attract them to our site... 10 / 50 Machine Learning for Digital Advertising - @datapythonist...
What is our goal? ...and sell our product. 11 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachd...
How does it work? 12 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
How does it work? The user journey 13 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
How does it work? The user journey 14 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
How does it work? The user journey 15 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
How does it work? The user journey 16 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
How does it work? The user journey 17 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
Ad exchange point of view 18 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
Ad exchange point of view How the ad exchange works? A publisher has an available ad space. 19 / 50 Machine Learning for D...
Ad exchange point of view How the ad exchange works? Advertisers bid for their ads on the cost for a click. bid: £0.35 bid...
Ad exchange point of view How the ad exchange make money? income = bid · clicks impressions (1) Impressions are constant r...
Ad exchange point of view What is the best option? bid: £0.35 expected clicks (for 1000 impressions): 25 expected profit (f...
E-commerce point of view 23 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
E-commerce point of view T-shirt e-commerce example 24 / 50 Machine Learning for Digital Advertising - @datapythonista - @...
E-commerce point of view Income statement1 Sales £23.89 100% Cost of goods sold £11.72 60% Delivery £4.36 18.25% Payment g...
E-commerce point of view Not so easy to make money... 26 / 50 Machine Learning for Digital Advertising - @datapythonista -...
An optimization problem 27 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
An optimization problem What can be optimized? Higher prices (added value, branding...) Lower production costs Leverage ma...
An optimization problem Conversion rate optimization: the numbers income = average_price · margin · num_sales − average_cp...
An optimization problem Conversion rate optimization: Features 30 / 50 Machine Learning for Digital Advertising - @datapyt...
An optimization problem Features: Users What Facebook, Google... know about our users? Age Gender Location Interests / Pag...
An optimization problem Features: Ads 32 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
An optimization problem Features: Website 33 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdi...
An optimization problem Features: Summary Users Age Gender Location Interests Friends Sociocultural status ... Ads Source ...
An optimization problem An amazing dataset Age 28 Gender female Location Lewisham Occupation receptionist Interests hiking...
An optimization problem What could we get from a dataset like this? Women aged 25 to 35 buy shoes on rainy Sundays Users l...
An optimization problem Amazed? 37 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
Introduction to machine learning 38 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
Introduction to machine learning So, what is machine learning? Different definitions A fancy word for statistics The science...
Introduction to machine learning What can machine learning do? It can accurately compute the probability of a certain user...
Introduction to machine learning How does machine learning work? 41 / 50 Machine Learning for Digital Advertising - @datap...
Introduction to machine learning How does machine learning work? 42 / 50 Machine Learning for Digital Advertising - @datap...
Introduction to machine learning Some maths Prclick = 1 1 + e−(β0+β1·x1+β2·x2) (3) 43 / 50 Machine Learning for Digital Ad...
Introduction to machine learning More complex models: neural networks 44 / 50 Machine Learning for Digital Advertising - @...
Machine learning for digital advertising 45 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdig...
Machine learning for digital advertising Some problems Data is expensive (average of £0.20 per row) :( No public data So, ...
Machine learning for digital advertising More problems We bias the data when we know who is more likely to buy Exploration...
Machine learning for digital advertising He is very sad now 48 / 50 Machine Learning for Digital Advertising - @datapython...
Machine learning for digital advertising What models can be used? Some techniques that gave good results: Gradient boostin...
Machine learning for digital advertising Questions? @datapythonista http://datapythonista.github.io https://www.linkedin.c...
Upcoming SlideShare
Loading in …5
×

Machine Learning for Digital Advertising

690 views

Published on

When using TV, radio, or street banners for our company marketing, it is difficult to assess what in our campaign is working, and what is not. But when using digital marketing, we can access a large amount of information to identify what we are doing right and what we are doing wrong.

For a given user that clicks on our ad, we can find information such as:
* What was the appearance of the ad? Texts, words used, image, colours...
* What kind of user we targeted? Age, gender, location, language...
* Which experience we offered to the user? Appearance of the landing page, number of clicks required to achieve the goal, information requested in forms...

As advertisers, we have a lot of control on all these variables, we decide what is the UX of our site, the graphical design of our ads, the users that we are targeting... With some basic analysis we can easily identify which ad is performing better, which are the main market segments that buy our products, or which is the page layout that maximizes sales. But this is only a small part of what we can do, by tracking all the available information, mining it, and using machine learning to take the right decisions in real time.

This talk will briefly describe what is direct response digital marketing, which is the information available, and what makes digital marketing information different of other domain datasets. We will see for example, that we are in an unbalanced problem, or that one of the keys is the computational performance of our model predictions.

Published in: Business
no profile picture user

  • Login to see the comments

Machine Learning for Digital Advertising

  1. 1. Machine Learning for Digital Advertising Marc Garcia Outreach digital - June 14th, 2016 1 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  2. 2. Digital advertising: a data scientist point of view 2 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  3. 3. Digital advertising: a data scientist point of view What is the Internet? A lot of bored people... 3 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  4. 4. Digital advertising: a data scientist point of view ...who use a gadget... 4 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  5. 5. Digital advertising: a data scientist point of view ...to access useless sites. 5 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  6. 6. Digital advertising: a data scientist point of view Ok, some of them are looking for something. 6 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  7. 7. What is our goal? 7 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  8. 8. What is our goal? Get their money! 8 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  9. 9. What is our goal? That’s the truth, but let’s say it in a more subtle way... 9 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  10. 10. What is our goal? We want to attract them to our site... 10 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  11. 11. What is our goal? ...and sell our product. 11 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  12. 12. How does it work? 12 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  13. 13. How does it work? The user journey 13 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  14. 14. How does it work? The user journey 14 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  15. 15. How does it work? The user journey 15 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  16. 16. How does it work? The user journey 16 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  17. 17. How does it work? The user journey 17 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  18. 18. Ad exchange point of view 18 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  19. 19. Ad exchange point of view How the ad exchange works? A publisher has an available ad space. 19 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  20. 20. Ad exchange point of view How the ad exchange works? Advertisers bid for their ads on the cost for a click. bid: £0.35 bid: £0.20 20 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  21. 21. Ad exchange point of view How the ad exchange make money? income = bid · clicks impressions (1) Impressions are constant regardless of the ad Bids are known for each ad Clicks are unknown, but can be predicted 21 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  22. 22. Ad exchange point of view What is the best option? bid: £0.35 expected clicks (for 1000 impressions): 25 expected profit (for 1000 impressions): £8.75 bid: £0.20 expected clicks (for 1000 impressions): 47 expected profit (for 1000 impressions): £9.40 22 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  23. 23. E-commerce point of view 23 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  24. 24. E-commerce point of view T-shirt e-commerce example 24 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  25. 25. E-commerce point of view Income statement1 Sales £23.89 100% Cost of goods sold £11.72 60% Delivery £4.36 18.25% Payment gateway £0.84 3.5% Total direct costs £19.53 81.75% Available for marketing £4.36 18.25% Average cost-per-click £0.20 Conversion rate (break-even) 22 1 Excludes many costs (product returns, freight-in, development, support, hardware, salaries, etc.) 25 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  26. 26. E-commerce point of view Not so easy to make money... 26 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  27. 27. An optimization problem 27 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  28. 28. An optimization problem What can be optimized? Higher prices (added value, branding...) Lower production costs Leverage marketing costs Virality (share on social networks...) Recurrence (newsletter to customers...) Conversion rate optimization Targeting / market segmentation Ad optimization Website optimization (A/B testing...) 28 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  29. 29. An optimization problem Conversion rate optimization: the numbers income = average_price · margin · num_sales − average_cpc · num_clicks (2) 29 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  30. 30. An optimization problem Conversion rate optimization: Features 30 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  31. 31. An optimization problem Features: Users What Facebook, Google... know about our users? Age Gender Location Interests / Pages visited Friends / Interactions Sociocultural status ... mostly everything What do we know about them? Not much individually We can access aggregated data 31 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  32. 32. An optimization problem Features: Ads 32 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  33. 33. An optimization problem Features: Website 33 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  34. 34. An optimization problem Features: Summary Users Age Gender Location Interests Friends Sociocultural status ... Ads Source Message Type (image, text,...) Placement Site ... Website Layout Colours, font size... Content density Offers, reviews... Conditions (delivery, returns) Steps to purchase ... Other User behaviour Day of week Time Weather Social environment ... 34 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  35. 35. An optimization problem An amazing dataset Age 28 Gender female Location Lewisham Occupation receptionist Interests hiking, salsa Education university Device smartphone Source Google search Placement top Ad type image Message type sales offer Web layout basic Web main colour green Conditions free delivery Returns free Product type shoes Quality high Price £79 Day business day Time evening Purchase true 35 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  36. 36. An optimization problem What could we get from a dataset like this? Women aged 25 to 35 buy shoes on rainy Sundays Users leave pages with more than 800 characters on the layout quite fast People from city A buy more product X, while people from city B, prefer product Y Ads with red colours have more clicks, but we get less conversions from them And all this means higher profits. 36 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  37. 37. An optimization problem Amazed? 37 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  38. 38. Introduction to machine learning 38 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  39. 39. Introduction to machine learning So, what is machine learning? Different definitions A fancy word for statistics The science of programming computers, so we don’t tell them what to do, but we tell them how to learn what to do A set of techniques to implement statistical models that are able to predict, and find patterns in the data Similar concepts: Big data, data science, data mining, deep learning, artificial intelligence... 39 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  40. 40. Introduction to machine learning What can machine learning do? It can accurately compute the probability of a certain user, to click on a certain ad. bid: £0.35 Click probability: 0.025 Expected profit: £0.00875 bid: £0.20 Click probability: 0.047 Expected profit: £0.00940 A small difference in profit but at scale: multiply by 1bn daily Fb users: £650,000/day 40 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  41. 41. Introduction to machine learning How does machine learning work? 41 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  42. 42. Introduction to machine learning How does machine learning work? 42 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  43. 43. Introduction to machine learning Some maths Prclick = 1 1 + e−(β0+β1·x1+β2·x2) (3) 43 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  44. 44. Introduction to machine learning More complex models: neural networks 44 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  45. 45. Machine learning for digital advertising 45 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  46. 46. Machine learning for digital advertising Some problems Data is expensive (average of £0.20 per row) :( No public data So, we need to obtain it all ourselves... ...and it’s expensive :( Unbalanced / sparse data (1 purchase for 100 clicks) So, we need 100x the data... ...and it’s expensive :( High (or very high) dimensionality So, we need a huge number of rows to avoid the curse of dimensionality ...and it’s expensive :( 46 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  47. 47. Machine learning for digital advertising More problems We bias the data when we know who is more likely to buy Exploration an exploitation problem We have to buy "bad" clicks to avoid it Many categorical variables They don’t play well with many models Data seasonality Black Friday, sales, Christmas... Access to data Google, Facebook do not give access to raw data We have to use aggregated data And they do not let you cross variables We need to assume independence among them 47 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  48. 48. Machine learning for digital advertising He is very sad now 48 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  49. 49. Machine learning for digital advertising What models can be used? Some techniques that gave good results: Gradient boosting trees Active learning (semisupervised learning) Online learning (for data freshness) 49 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit
  50. 50. Machine learning for digital advertising Questions? @datapythonista http://datapythonista.github.io https://www.linkedin.com/in/datapythonista 50 / 50 Machine Learning for Digital Advertising - @datapythonista - @outreachdigit

×