16 years ago the authors signed off with this thought:
Agents might eventually be fellow team members with humans in the way a young child or a novice can be – subject to the consequences of brittle and literal-minded interpretation of language and events, limited ability to appreciate or even attend effectively to key aspects of the interaction, poor anticipation, and insensitivity to nuance.
We’ve still got a long way to go…
http://blog.acolyer.org/2020/01/10/ten-challenges-for-automation/
Agents might eventually be fellow team members with humans in the way a young child or a novice can be – subject to the consequences of brittle and literal-minded interpretation of language and events, limited ability to appreciate or even attend effectively to key aspects of the interaction, poor anticipation, and insensitivity to nuance.
We’ve still got a long way to go…
http://blog.acolyer.org/2020/01/10/ten-challenges-for-automation/
Taxonomy is a methodology that classifies entities and defines the hierarchical relationship among them. It’s widely used as a knowledge management system in the industry, and has proven success in improving the accuracy of the machine learning models in search, user-behavior modeling, and classification tasks.
https://medium.com/@Pinterest_Engineering/interest-taxonomy-a-knowledge-graph-management-system-for-content-understanding-at-pinterest-a6ae75c203fd
https://medium.com/@Pinterest_Engineering/interest-taxonomy-a-knowledge-graph-management-system-for-content-understanding-at-pinterest-a6ae75c203fd
Medium
Interest Taxonomy: A knowledge graph management system for content understanding at Pinterest
Song Cui, Dhananjay Shrouty | Software Engineers, Content Knowledge
The focus is how to identify what success means so that the machine learning algorithm (in this case based on multi-armed contextual bandits) captures that users differ into how they listen to music and playlist consumption varies a lot.
https://mounia-lalmas.blog/2018/10/11/personalizing-the-user-experience-and-playlist-consumption-on-spotify/
https://mounia-lalmas.blog/2018/10/11/personalizing-the-user-experience-and-playlist-consumption-on-spotify/
From the Lab to the Market
Personalizing the user experience and playlist consumption on Spotify
These are the slides of the talk I gave at the O’Reilly AI conference in London. My first external talk about work at Spotify on personalisation for Spotify home. The focus is how to identify…
List of publications about the intersection UX and ML in applied settings: https://mounia-lalmas.blog/publications/
From the Lab to the Market
Publications
Publications 2024 A Damianou, F Fabbri, P Gigioli, M De Nadai, A Wang, E Palumbo & M Lalmas. Towards Graph Foundation Models for Personalization, The Web Conference (Graph Foundation Models Wor…
Four projects in the intellectual history of quantitative social science
1. The rise and fall of game theory.
2. The disaster that is “risk aversion.”
3. From model-based psychophysics to black-box social psychology experiments.
4. The two models of microeconomics.
https://statmodeling.stat.columbia.edu/2020/01/12/four-projects-in-the-intellectual-history-of-quantitative-social-science/
1. The rise and fall of game theory.
2. The disaster that is “risk aversion.”
3. From model-based psychophysics to black-box social psychology experiments.
4. The two models of microeconomics.
https://statmodeling.stat.columbia.edu/2020/01/12/four-projects-in-the-intellectual-history-of-quantitative-social-science/
randomized controlled trial vs. front-door adjustment
In 2014, Adam Glynn and Konstantin Kashin, applied the new method to a data set well scrutinized by social scientists, called the Job Training Partnership Act (JTPA), conducted from 1987 to 1989.
Notably, the study included both a randomized controlled trial (RCT), where people were randomly assigned to receive services or not, and an observational study, in which people could choose for themselves.
Glynn and Kashin’s results show why the front-door adjustment is such a powerful tool: it allows us to control for confounders that we cannot observe (like Motivation), including those that we can’t even name.
https://scholar.harvard.edu/files/aglynn/files/glynnkashin-frontdoor.pdf
In 2014, Adam Glynn and Konstantin Kashin, applied the new method to a data set well scrutinized by social scientists, called the Job Training Partnership Act (JTPA), conducted from 1987 to 1989.
Notably, the study included both a randomized controlled trial (RCT), where people were randomly assigned to receive services or not, and an observational study, in which people could choose for themselves.
Glynn and Kashin’s results show why the front-door adjustment is such a powerful tool: it allows us to control for confounders that we cannot observe (like Motivation), including those that we can’t even name.
https://scholar.harvard.edu/files/aglynn/files/glynnkashin-frontdoor.pdf