Lift (data mining)

<p>In <a href="/facts/Data_mining/AH53q5ac">data mining</a> and <a href="/facts/Association_rule_learning/oX6w9Kux">association rule learning</a>, lift is a measure of the performance of a targeting <a href="/facts/Model_(abstract)/hgysE2kP">model</a> (association rule) at predicting or classifying cases as having an enhanced response (with respect to the population as a whole), measured against a random choice targeting model. A targeting model is doing a good job if the response within the target (
  
    
      
        T
      
    
    {\displaystyle T}
  
) is much better than the baseline (
  
    
      
        B
      
    
    {\displaystyle B}
  
) average for the population as a whole. Lift is simply the ratio of these values: target response divided by average response. Mathematically,
</p>

lift
        =
        
          
            
              P
              (
              T
              ∣
              B
              )
            
            
              P
              (
              T
              )
            
          
        
        =
        
          
            
              P
              (
              T
              ∧
              B
              )
            
            
              P
              (
              T
              )
              P
              (
              B
              )
            
          
        
      
    
    {\displaystyle \operatorname {lift} ={\frac {P(T\mid B)}{P(T)}}={\frac {P(T\wedge B)}{P(T)P(B)}}}

<p>For example, suppose a population has an average response rate of 5%, but a certain model (or rule) has identified a segment with a response rate of 20%. Then that segment would have a lift of 4.0 (20%/5%).
</p>

Lift (data mining) open-in-new

Lift (data mining)