Rice AnalyticsTM is a SAS Partner with broad experience in consumer, business, and scientific predictive modeling. We offer Reduced Error Logistic Regression (RELR) software (patent pending) and related consulting. RELR has these distinct advantages compared to standard predictive modeling methods:
- RELR models can have substantially less predictive error with smaller sample sizes.
- Because RELR models require significantly smaller sample sizes for accuracy, the data processing and data collection costs involving a RELR model can be a small fraction of the large expense that is often required with other predictive methods.
- This lower predictive error with smaller sample sizes becomes more dramatic as more candidate variables are in a RELR model. For this reason, RELR can build a model based upon high dimensional data involving large numbers of interaction variables and/or nonlinear variables at a very small sample size and generate an extremely accurate model.
- Predictive models involving high dimensionality due to two or three way interactions are usually not even feasible with other predictive methods because of run time restrictions, but RELR can run these types of models in a reasonable time in most standard business applications. In addition to its small sample size and batching feature to gain speed advantage, RELR runs with high dimensional data because it has a built-in variable shortlisting feature that serves to decrease the dimensionality of the candidate variables tremendously without any cost in accuracy.
- The variable selection method known as Parsed RELR can often select fewer than 10 variables from more than 50,000 candidate variables.
- Parsed RELR's regression coefficients usually have substantially less error compared to standard regression methods even at larger sample sizes.
- Because the regression coefficients have substantially reduced error, Parsed RELR appears to select variables and parameters with remarkable face validity given a minimal sample size.
- In contrast to Stepwise Logistic Regression, Parsed RELR has no arbitrary parameters and can be an entirely automated method. However, RELR users do have the ability to manually override any variable that is selected or choose variables not selected, as this can be helpful to select those variables that business customers wish to see in a model.
Recent News
June 15, 2009. St. Louis, MO (USA) - Dan Rice gave an invited address last week at the 2009 Classification Society Annual Conference from June 11-13 at the Washington University Medical School. This conference brought together roughly a hundred experts from major universities and businesses in the areas of machine learning, choice modeling, and classification research. This conference was truly international in scope and had attendees from many industrialized countries. However, the relatively small size of this conference compared to JSM allowed for an extended discussion between attendees over the course of several days. The title of this talk was "Reduced Error Logistic Regression". This talk can be downloaded from the Papers and Presentations page of this website.
June 3, 2009. St. Louis, MO (USA) - We have now updated the Case Studies page of this website with credit scoring results from three major banks and one credit card company. The most impressive result is that one user reports a lift from RELR in the KS statistic from roughly 40 to 65 compared to other methods.
February 12, 2009. St. Louis, MO (USA) - Rice Analytics, a SAS Alliance Partner, and the exclusive provider of Reduced Error Logistic Regression (RELR) software announced today that it is proud to be a sponsor of this year's Midwest SAS User Group Conference (MWSUG) in Cleveland, Ohio in October, 2009. Dan Rice was a speaker at the 2008 MWSUG conference in a session on Reduced Error Logistic Regression. The MWSUG is one of the larger regional statistical conferences - approximately 300 people attended the 2008 conference in Indianopolis, Indiana.
September 2, 2008. St. Louis, MO (USA) - Rice Analytics announced today that it has invented a process to reduce the number of variables in RELR models substantially. This process is called Parsed Reduced Error Logistic Regression, or ParsedTM RELR. Like Full RELR, Parsed RELR gives accurate validation sample models with relatively small amounts of overfitting. Like Full RELR, Parsed RELR is suited for high dimensional datasets with hundreds of thousands of input variables and interactions. However, Parsed RELR gives extremely parsimonious solutions that often select fewer than ten variables with high dimensional and multicollinear datasets that might require hundreds of variables for an accurate Full RELR model. While other predictive modeling methods can select few variables, these same few variables are unlikely to be selected in models built from independent samples, so they have little explanatory meaning. In contrast, due to the error reduction features inherent in RELR, the same variables are likely to be selected in Parsed RELR models built from independent samples at much smaller sample sizes than is possible with other methods. Parsed RELR opens the door to highly accurate predictive models that are not just predictive, but also potentially explanatory.
August 6, 2008. Denver, CO (USA) - Daniel M. Rice, Ph.D. spoke today at the Data Mining and Machine Learning Session of the 2008 Joint Statistical Meetings in Denver, Colorado. This session was chaired by Bill Heavlin of Google Inc. and had very good speakers from the United States Army, Medical University of China, University of Alabama, Bell Labs, and the University of California at Berkeley. This session was extremely well attended with a standing-room-only crowd. This standing-room-only crowd and the lively discussions prompted Bill Heavlin to say that this session "was the very best session at the conference". The title of Rice's talk was "Generalized Reduced Error Logistic Regression Machine". In this presentation, Rice provided very good evidence that Reduced Error Logistic Regression is able to reduce error significantly compared to Penalized Logistic Regression, Step-Wise Logistic Regression and four other standard methods. A full article coinciding with this talk and published in JSM 2008 Proceedings can be downloaded from the Papers and Presentations page of this website. The Joint Statistical Meetings is one of the largest gatherings of statisticians in the world. Approximately 5000 people attended this conference in Denver this summer.
