RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
cc @JonoBone @tomwsymons
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @MDRC_News: Using #MachineLearning, hundreds of researchers tried to predict 6 life outcomes, such as a child’s GPA & whether a family w…
RT @MDRC_News: Using #MachineLearning, hundreds of researchers tried to predict 6 life outcomes, such as a child’s GPA & whether a family w…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @alliecmorgan: I'm honored to contribute to this project and so excited to see it finally out! An inspirational collaborative effort to…
RT @IanLundberg1: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outc…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @alliecmorgan: I'm honored to contribute to this project and so excited to see it finally out! An inspirational collaborative effort to…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
Not surprised
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
Interesting perspective on prediction
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
This is pretty important work.
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @IanLundberg1: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outc…
#collaborativej, #collaborativescience: makes better sense & closer to the truth.
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
Great thread on the Fragile Families Challenge. I'm proud to have been able to play a small role in it. Thanks @msalganik @IanLundberg1 @alextkindel and others for the heroic effort to organize this!
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @amaatouq: Such an honor to play a small part in this truly inspirational collaborative effort (led by @msalganik @IanLundberg1 @alextki…
RT @amaatouq: Here is a great thread by @msalganik on the FFC! https://t.co/ILT4JSviet
Here is a great thread by @msalganik on the FFC! https://t.co/ILT4JSviet
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
This project & associated papers look like a fantastic resource for anyone interested in computational reproducibility, robustness/multiverse analyses, or the challenges of running mega-collaborations.
It was so awesome to get to work on this and I’m so glad to see it in the world! As always, @msalganik constantly challenges how I think about science and what’s possible to do as a researcher.
Proud to have been a part of the challenge! This work is crucial to the future of the quantitative social sciences
RT @IanLundberg1: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outc…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
Here is also great summary of the FFC Challenge https://t.co/84DA6myYLt
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
RT @msalganik: If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcome…
Paper at https://t.co/WxDJbw0joz. Replication materials at https://t.co/GlhIDOWoNl.
Paper at https://t.co/kuYGpjVlKq. Replication materials at https://t.co/IYx9o2IYTa.
If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcomes? Not very well. Fragile Families Challenge: paper in PNAS w 112 authors https://t.co/WxDJbw0joz & Special Collection of Sociu
If hundreds of scientists created predictive algorithms with high-quality data, how well would the best predict life outcomes? Not very well. Fragile Families Challenge: paper in PNAS w 112 authors https://t.co/kuYGpjVlKq & Special Collection of Sociu
RT @random_walker: Predicting the future is hard, whether you use a magic 8-ball or machine learning. New in PNAS—160 teams competed to pre…
RT @random_walker: Predicting the future is hard, whether you use a magic 8-ball or machine learning. New in PNAS—160 teams competed to pre…
@a_berut @Uneheuredepeine Je signale aussi cet article qui rapporte les résultats d'une sorte de datathon entre spécialistes du machine-learning pour prévoir les résultats d'une enquête en cours (spoiler, ils ne font pas mieux qu'une bête régression). Très
Social scientists weren't able to predict life trajectories at all using large data sets and AI/ML. https://t.co/8QaJn7r0c4
RT @Jeibros: Machine-learning usado para hacer cualquier tipo de predicción. Prácticamente solo un poco mejor que Sandro Rey.
@isiAfrica I'd highlight this as well. Yes, AI (&data-driven tools) are about intervening. They cannot predict or manage populations but being accurate it is not the purpose. This is something we found regularly in our case studies. 👇🏾 https://t.co/I3
RT @random_walker: Predicting the future is hard, whether you use a magic 8-ball or machine learning. New in PNAS—160 teams competed to pre…
Tan importante es saber para que sirve una tecnología como saber para qué NO sirve. La inteligencia Artificial no sirve para predecir el futuro de la gente. 160 equipos intentan predecir la vida de familias en riesgo y no mejoran mucho a las predicciones a
RT @Jeibros: Machine-learning usado para hacer cualquier tipo de predicción. Prácticamente solo un poco mejor que Sandro Rey. https://t.co/…
Machine-learning usado para hacer cualquier tipo de predicción. Prácticamente solo un poco mejor que Sandro Rey.
Measuring the predictability of life outcomes with a scientific mass collaboration | PNAS https://t.co/TKcQs47yeR
'Measuring the predictability of life outcomes with scientific mass collaboration' by nopinsight Read more about this story here --> https://t.co/L7vF2hx7xc
RT @duncanjwatts: Proud to be associated with this breakthrough collaborative effort, unprecedented (I believe) in the social sciences. Hug…
Measuring the predictability of life outcomes with a scientific mass collaboration https://t.co/V1DujRoCTu
Measuring the predictability of life outcomes with a scientific https://t.co/hOI6E81k0I
Für die Bildungsbubble: Langzeitstudie zeigt, dass maschinelle Prognosen von Lebensläufen nicht möglich sind: https://t.co/grIbppvIE9 #KI
RT @nemmen: This is why we are very far away from the Rehoboam AI portrayed in @WestworldHBO season 3. Paper: https://t.co/vAD5iVDjYq https…
metodos basados en ML fueron largamente imprecisos en predecir 6 resultados en data del estudio familias frágiles. Ojo con alerta temprana @MinDesarrollo / Measuring the predictability of life outcomes with a scientific mass collaboration https://t.co/3zDV
bu sonuçlar bir takım endişeleri doğurmaktadır. Genel olarak, bu sonuçlar bazı ortamlarda yaşam gidişatının tahminin öngörülebilirliğine pratik sınırlar getirmekte ve sosyal bilimlerdeki disiplinlerarası çalışmaların değerini göstermektedir. Kaynak: https:
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @jomuzhi: Social science is seldom about prediction but more about explanations, though ppl care more about Prediction...
Social science is seldom about prediction but more about explanations, though ppl care more about Prediction...
This is why we are very far away from the Rehoboam AI portrayed in @WestworldHBO season 3. Paper: https://t.co/vAD5iVDjYq https://t.co/W3IpAJe5Js
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
Practical limits to the predictability of life outcomes...
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
Turns out predicting the future really is difficult! 😬 New @PNASNews paper out that demonstrates how hard it is to predict a variety of life outcomes, even with a variety of models. Amazing collaborative effort, too 💪🏼🎉💯
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
Measuring the predictability of life outcomes with a scientific mass collaboration https://t.co/Shq2rjuXfo
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @AnttiLatvala: RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews with our @ridhikash07 @OxfordDemSci led by @msalganik in massive collaboration https://t.co/eYL
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…
RT @melindacmills: #MachineLearning models predict life trajectories only slightly better than simple benchmark model - new @PNASNews wit…