Researchers at Princeton, Columbia and Harvard have created a new method to analyze big data that better predicts outcomes in health care, politics and other fields.
The study appears this week in the journal Proceedings of the National Academy of Sciences. A PDF is available on request.
In previous studies, the researchers showed that significant variables might not be predictive and that good predictors might not appear statistically significant. This posed an important question: how can we find highly predictive variables if not through a guideline of statistical significance? Common approaches to prediction include using a significance-based criterion for evaluating variables to use in models and evaluating variables and models simultaneously for prediction using cross-validation or independent test data.
In an effort to reduce the error rate with those methods, the researchers proposed a new measure called the influence score, or I-score, to better measure a variable’s ability to predict. They found that the I-score is effective in differentiating between noisy and predictive variables in big data and can significantly improve the prediction rate. For example, the I-score improved the prediction rate in breast cancer data from 70 percent to 92 percent. The I-score can be applied in a variety of fields, including terrorism, civil war, elections and financial markets.
“The practical implications are what drove the project, so they’re quite broad,” says lead author Adeline Lo, a postdoctoral researcher in Princeton’s Department of Politics. “Essentially anytime you might be interested in predicting and identifying highly predictive variables, you might have something to gain by conducting variable selection through a statistic like the I-score, which is related to variable predictivity. That the I-score fares especially well in high dimensional data and with many complex interactions between variables is an extra boon for the researcher or policy expert interested in predicting something with large dimensional data.”
The Latest on: Prediction tool
via Google News
The Latest on: Prediction tool
- Cambridge Crystallographic Data Centre simplifies management of complex crystal structure prediction (CSP) dataon April 13, 2021 at 4:00 pm
The Cambridge Crystallographic Data Centre ( CCDC) announces the launch of CSD-Theory software for use in small molecule pharmaceutical development. This latest addition to the CCDC’s software toolbox ...
- Bitcoin (Btc) Price Prediction: Btc/USD Breaches Crucial Resistance Levels, Pauses Above $63,000 Highon April 13, 2021 at 3:52 pm
Price Prediction – April 13, 2021 From every indication, Bitcoin bulls have broken the resistance at $60,000 and $61,800. The price surge has continued above the $ ...
- ImpriMed Raises $8M to Commercialize AI-Driven Personalized Drug Response Prediction Service in ...on April 13, 2021 at 5:02 am
“HG Initiative along with other investors, is a welcome endorsement for ImpriMed’s AI-Driven Personalized Chemo Response Prediction tool and its viability,” said Dr. Sungwon Lim, CEO and Co-Founder at ...
- ImpriMed Raises $8M to Commercialize AI-Driven Personalized Drug Response Prediction Service in Pet Cancer Marketon April 13, 2021 at 5:01 am
“HG Initiative along with other investors, is a welcome endorsement for ImpriMed’s AI-Driven Personalized Chemo Response Prediction tool and its viability,” said Dr. Sungwon Lim, CEO and Co ...
- The Evolution of Ransomware: Four Predictions to Shape Your Security Strategyon April 13, 2021 at 4:00 am
For organizations faced with highly sophisticated and targeted attacks from well-resourced cybercrime groups, standard AV and EDR platforms are of little use against ransomware.
- The whole is greater than its parts: ensembling improves protein contact predictionon April 13, 2021 at 3:31 am
We also show that ensembling these recent deep neural networks with the best CASP13 group creates a superior contact prediction tool. Finally, we demonstrate that two ensembled networks can ...
- Global Downhole Tools Market Covering Prime Factors and Competitive Outlook till 2026on April 12, 2021 at 4:42 am
The key market players include Excalibre Downhole Tools Ltd., Bilco Tools Inc., Baker Hughes Inc., Schlumberger Ltd., Wenzel Downhole Tools Ltd., Oil States International Inc. Request Sample Report of ...
- Prediction of ambulatory outcome in patients with corona radiata infarction using deep learningon April 12, 2021 at 2:47 am
In the prediction of ambulatory function with the validation dataset ... Therefore, it should be used as a supplementary tool for clinicians to predict long-term ambulatory outcomes. In addition, we ...
- Logicserve Digital launches predictive analytics tool Traffic Cost Predictoron April 6, 2021 at 5:23 am
It makes use of historical data from Google Analytics and monthly spends. 06 Apr, 2021 - 05:53 PM IST | By indiantelevision.com Team NEW DELHI: Hair colour brand Streax, from Hygienic Research ...
via Bing News