Home      Discussion      Topics      Dictionary      Almanac
Signup       Login
Accuracy paradox

Accuracy paradox

Overview
The accuracy paradox for predictive analytics
Predictive analytics
Predictive analytics encompasses a variety of techniques from statistics, data mining and game theory that analyze current and historical facts to make predictions about future events....

 states that predictive models with a given level of accuracy may have greater predictive power
Predictive power
The predictive power of a scientific theory refers to its ability to generate testable predictions. Theories with strong predictive power are highly valued, because the predictions can often encourage the falsification of the theory...

 than models with higher accuracy. It may be better to avoid the accuracy metric in favor of other metrics such as precision
Precision
Precision has the following meanings:Concepts* Accuracy and precision, measurement deviation from true value and its scatter* Precision , the number of digits from which a value is expressed...

 and recall
Recall
Recall may refer to:*Product recall*Recall election*Letter to recall sent to return an ambassador from a country, either as a diplomatic protest or because the diplomat is being reassigned elsewhere and is being replaced by another envoy...

.

Accuracy is often the starting point for analyzing the quality of a predictive model, as well as an obvious criterion for prediction. Accuracy measures the ratio of correct predictions to the total number of cases evaluated.
Discussion
Ask a question about 'Accuracy paradox'
Start a new discussion about 'Accuracy paradox'
Answer questions from other users
Full Discussion Forum
 
Encyclopedia
The accuracy paradox for predictive analytics
Predictive analytics
Predictive analytics encompasses a variety of techniques from statistics, data mining and game theory that analyze current and historical facts to make predictions about future events....

 states that predictive models with a given level of accuracy may have greater predictive power
Predictive power
The predictive power of a scientific theory refers to its ability to generate testable predictions. Theories with strong predictive power are highly valued, because the predictions can often encourage the falsification of the theory...

 than models with higher accuracy. It may be better to avoid the accuracy metric in favor of other metrics such as precision
Precision
Precision has the following meanings:Concepts* Accuracy and precision, measurement deviation from true value and its scatter* Precision , the number of digits from which a value is expressed...

 and recall
Recall
Recall may refer to:*Product recall*Recall election*Letter to recall sent to return an ambassador from a country, either as a diplomatic protest or because the diplomat is being reassigned elsewhere and is being replaced by another envoy...

.

Accuracy is often the starting point for analyzing the quality of a predictive model, as well as an obvious criterion for prediction. Accuracy measures the ratio of correct predictions to the total number of cases evaluated. It may seem obvious that the ratio of correct predictions to cases should be a key metric. A predictive model may have high accuracy, but be useless.

In an example predictive model for an insurance fraud
Insurance fraud
Insurance fraud is any act committed with the intent to fraudulently obtain payment from an insurer.Insurance fraud has existed ever since the beginning of insurance as a commercial enterprise. Fraudulent claims account for a significant portion of all claims received by insurers, and cost billions...

 application, all cases that are predicted as high-risk by the model will be investigated. To evaluate the performance of the model, the insurance company has created a sample data set of 10,000 claims. All 10,000 cases in the validation
Validation
The word validation has several uses:* In common usage, validation is the process of checking if something satisfies a certain criterion. Examples would include checking if a statement is true , if an appliance works as intended, if a computer system is secure, or if computer data are compliant...

 sample have been carefully checked and it is known which cases are fraudulent. To analyze the quality of the model, the insurance uses the table of confusion. The definition of accuracy, the table of confusion for model M1Fraud, and the calculation of accuracy for model M1Fraud is shown below.


A(M) = (TN + TP) / (TN + FP + FN + TP)
where
TN is the number of true negative cases
FP is the number of false positive cases
FN is the number of false negative cases
TP is the number of true positive cases


Formula 1: Definition of Accuracy


Predicted Negative Predicted Positive
Negative Cases 9,700 150
Positive Cases 50 100


Table 1: Table of Confusion for Fraud Model M1Fraud.


A(M) = (9,700 + 100) / (9,700 + 150 + 50 + 100) = 98.0%


Formula 2: Accuracy for model M1Fraud

With an accuracy of 98.0% model M1Fraud appears to perform fairly well. The paradox lies in the fact that accuracy can be easily improved to 98.5% by always predicting "no fraud". The table of confusion and the accuracy for this trivial “always predict negative” model M2Fraud and the accuracy of this model are shown below.


Predicted Negative Predicted Positive
Negative Cases 9,850 0
Positive Cases 150 0


Table 2: Table of Confusion for Fraud Model M2Fraud.


A(M) = (9,850 + 0) / (9,850 + 0 + 150 + 0) = 98.5%


Formula 3: Accuracy for model M2Fraud

Model M2Fraudreduces the rate of inaccurate predictions from 2% to 1.5%. This is an apparent improvement of 25%. The new model M2Fraud shows fewer incorrect predictions and markedly improved accuracy, as compared to the original model M1Fraud, but is obviously useless.

The alternative model M2Fraud does not offer any value to the company for preventing fraud. The less accurate model is more useful than the more accurate model.

Model improvements should not be measured in terms of accuracy gains. It may be going too far to say that accuracy is irrelevant, but caution is advised when using accuracy in the evaluation of predictive models.

See also

  • Receiver operating characteristic
    Receiver operating characteristic
    In signal detection theory, a receiver operating characteristic , or simply ROC curve, is a graphical plot of the sensitivity vs. for a binary classifier system as its discrimination threshold is varied. The ROC can also be represented equivalently by plotting the fraction of true positives vs...

    for other measures of how good model predictions are.