intelligence in finn
play

Intelligence in FINN DND Software 2020 Nicolai Hge 2008 Nicolai - PowerPoint PPT Presentation

Use of Artificial Intelligence in FINN DND Software 2020 Nicolai Hge 2008 Nicolai Hge 2001 - 2006 1999 - 2001 2006 - 2008 Hva skal jeg snakke om? Hva er kunstig intelligens og maskinlring? To konkrete eksempler fra FINN:


  1. Use of Artificial Intelligence in FINN DND Software 2020 Nicolai Høge

  2. 2008 Nicolai Høge 2001 - 2006 1999 - 2001 2006 - 2008

  3. Hva skal jeg snakke om? • Hva er kunstig intelligens og maskinlæring? • To konkrete eksempler fra FINN: • Annonsekontroll • Anbefalinger • Hva har vi lært etter 5+ år ?

  4. What is Artificial Intelligence? ● To get machines to solve tasks, that humans need intelligence to do ● Most of the work around (AI) is open and available to everyone. That means that knowledge is not the key, but rather the access to data and competent people ● Many sub categories ○ NLP, ML, Image Recognition etc.

  5. Why is everybody talking about Machine Learning? The computer learns how to categorize or group input Without ML Supervised Unsupervised Input Input Output Model Input Model Algorithm Output

  6. Ad Control

  7. Machine Learning for Ad Control Store the results Ad 500 000 changes pr / week 1 . Control 2. 3.

  8. Human rules, manual weighting

  9. ML weighting of rules From manual weighting to ML weighting of rules

  10. ML generated rules From manual rules to ML generated rules

  11. Train model with more data Train the ML model with more data

  12. Keep tuning until “good enough”

  13. Recommendations

  14. One visit, many signals 100 different signals pageviews recommendation inscreen contact_action search ... Typically 100 signals pr. visit

  15. Many visits, A LOT of signals 200-300 million signals pr. day Data lake 9 TB

  16. From signals to recommendations AB testing Data lake 9 TB Machine Learning 30 - 40 models ● Experimentation ● Always 3-4 different ● algorithms running against each other Validation of models in ● production

  17. Recommendations based on users or objects or Input Recommendation Output Service

  18. One engine, many products Personalized search BLINK Recommendations Use signals to improve Recommendation recommendations Service

  19. Results CTR 30% 1000 clicks/ min

  20. What is under the hood?

  21. Combining more than one model ● Collaborative Filtering works with a lot of data ● Confused with little data ● Combine text, image and collaborative filtering KDD 2018: Eide, Zhou, Øygard: Five lessons from building a deep neural network recommender

  22. More relevant results

  23. When things go wrong...

  24. ...and challenges Our success factors... ● Difficult to recruit the right ● Data Scientists are part of the people product development teams ● Hard to gather data ● Tons of experiments ● The models are only as good ● Our ability to create products as the data they learn from ● Off the shelves models may be good enough, but you probably need use them in inventive ways

Recommend


More recommend