LGDtoolkit (version 0.2.0)

interaction.transformer: Extract risk factors interaction from decision tree

Description

interaction.transformer extracts the interaction between supplied risk factors from decision tree. It implements customized decision tree algorithm that takes into account different conditions such as minimum percentage of observations and defaults in each node, maximum tree depth and monotonicity condition at each splitting node. Sum of squared errors is used as metric for node splitting .

Usage

interaction.transformer(
  db,
  rf,
  target,
  min.pct.obs,
  min.avg.rate,
  max.depth,
  monotonicity,
  create.interaction.rf
)

Value

The command interaction.transformer returns a list of two data frames. The first data frame provides the tree summary. The second data frame is a new risk factor extracted from decision tree.

Arguments

db

Data frame of risk factors and target variable supplied for interaction extraction.

rf

Character vector of risk factor names on which decision tree is run.

target

Name of target variable within db argument.

min.pct.obs

Minimum percentage of observation in each leaf.

min.avg.rate

Minimum average target rate in each leaf..

max.depth

Maximum number of splits.

monotonicity

Logical indicator. If TRUE, observed trend between risk factor and target will be preserved in splitting node.

create.interaction.rf

Logical indicator. If TRUE, second element of the output will be data frame with interaction modalities.

Examples

library(LGDtoolkit)
data(lgd.ds.c)
it <- LGDtoolkit::interaction.transformer(db = lgd.ds.c,
		              rf = c("rf_01", "rf_03"), 
                             target = "lgd",
                             min.pct.obs = 0.05,
                             min.avg.rate = 0.01,
                             max.depth = 2,
                             monotonicity = TRUE,
                             create.interaction.rf = TRUE)
names(it)
it[["tree.info"]]
tail(it[["interaction"]])
table(it[["interaction"]][, "rf.inter"], useNA = "always")