RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @jsradford: Reminds me of the debate @MishaTeplitskiy and I have about sociology's 'dark matter' - our persistently low r-squared. I sug…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
such systems have been crimped or terminated for their un-PC findings, in the past - expect the same here -
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Predicting child outcomes is really hard. Convincingly demonstrated by Sara McLanahan and large group of coauthors in PNAS today. I wonder how much of difficulty is due to the reliability of the self-reported survey outcomes? https://t.co/PlFeu2ccdg
How good are we at using machine-learning to predict life trajectories? Answer: at best, "not very accurate" and "only slightly better than [predictions] from a simple benchmark model". See the study in @PNASNews by @msalganik and dozens of co-authors: htt
Reminds me of the debate @MishaTeplitskiy and I have about sociology's 'dark matter' - our persistently low r-squared. I suggested we were under-using our information. He suggested it's measurement error. This is good evidence that I'm wrong.
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @autismcrisis: "Hundreds of researchers attempted to predict six life outcomes" but "no one made very accurate predictions"? https://t.c…
RT @hcp4715: "These researchers used machine-learning methods optimized for prediction, and they drew on a vast dataset that was painstakin…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chrishanretty: Life is not very predictable (and machine learning doesn't improve much over domain knowledge and logistic regression)…
RT @chrishanretty: Life is not very predictable (and machine learning doesn't improve much over domain knowledge and logistic regression)…
Life is not very predictable (and machine learning doesn't improve much over domain knowledge and logistic regression) https://t.co/cZlDjGoDPm (h/t @TahaYasseri)
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
"These researchers used machine-learning methods optimized for prediction, and they drew on a vast dataset that was painstakingly collected by social scientists over 15 y. However, no one made very accurate predictions. "😂 https://t.co/IMeweeteRN
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Thread: that shows people & societies are complex, no one made very accurate predictions
RT @autismcrisis: "Hundreds of researchers attempted to predict six life outcomes" but "no one made very accurate predictions"? https://t.c…
In the co-authored study below, which has been just published in @PNASNews, this question is investigated through the analysis of a #scientific #mass #collaboration project held within the Fragile Families Challenge competition. https://t.co/EOlNBlFwZI
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Measuring the predictability of life outcomes with a scientific mass collaboration https://t.co/eR09aPY5tK
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @ChrisDanforth: Predicting life outcomes is hard: "Despite using a rich dataset & machine-learning methods... the best predictions were…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @autismcrisis: "Hundreds of researchers attempted to predict six life outcomes" but "no one made very accurate predictions"? https://t.c…
RT @autismcrisis: "Hundreds of researchers attempted to predict six life outcomes" but "no one made very accurate predictions"? https://t.c…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @autismcrisis: "Hundreds of researchers attempted to predict six life outcomes" but "no one made very accurate predictions"? https://t.c…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @BeEngelhardt: Extremely excited to see the Fragile Families Challenge paper out. @msalganik asked if ML worked to predict life outcomes…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Significance: "No one made very accurate predictions." Could this outcome have been inferred from the data sets (PCA?) without having to use Machine Learning? Measuring the predictability of life outcomes with a scientific mass collaboration https://t.co
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Fantastic (short) thread of a fascinating paper.
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
All that machine learning techies and policymakers are so excited about bc it’ll predict social outcomes? Well, it’s malarkey.
@FFCWS @NICHD_NIH
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Cool study! Only problem is I can’t ever cite it or I’d immediately be over the word count.
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
Really important ⬇️⬇️
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @_MikeKiser: The Fragile Families (@FFCWS) paper is out . If you heard my talk about ethics in AI at @RSAConference with @BDayanim this…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @Zoe_LeBlanc: this is fascinating!! CSS giant study on value of ML "only somewhat better than the results from a simple benchmark model…
RT @Zoe_LeBlanc: this is fascinating!! CSS giant study on value of ML "only somewhat better than the results from a simple benchmark model…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @chris_bail: 1/n Can machine learning solve social science problems? This unprecedented study led by @msalganik and dozens of co-authors…
RT @Zoe_LeBlanc: this is fascinating!! CSS giant study on value of ML "only somewhat better than the results from a simple benchmark model…