detectTimeVariations {matman}

Detects items whose value (stock, demand, etc.) has changed over time

Description

Detects items whose value (stock, demand, etc.) has changed over time in contrast to other items. This analysis is based on the Macnaughton-Smith et al. clustering algorithm.

Usage

detectTimeVariations(
  data,
  value,
  item,
  timestamp,
  temporalAggregation = c("day", "week", "month", "quarter", "year"),
  aggregationFun = sum,
  preProcess = NA,
  recentTimePeriods = 5
)

Arguments

data

Data frame that will be expanded.

value

Name of the column variable that contains the value for the ABC and XYZ analysis.

item

Name of the column including the item names or identifiers (e.g., product name, EAN)

timestamp

Name of the column including the timestamp. This column should be in POSIX or Date-format.

temporalAggregation

Temporal aggregation mode (i.e., "day", "week", "month", "quarter", "year").

aggregationFun

Function for aggregating the value column. Default is sum.

preProcess

A string vector that defines a pre-processing of the aggregated data before clustering. Available pre-processing methods are "center", "scale", "standardize", and "normalize". Default is NA (no pre-processing).

recentTimePeriods

Integer indicating the number of time periods that are used to define the recent item values. Default is 5.

Value

Returns a data frame showing to which cluster each item belongs based on all value and based on the recent values as well as whether the item has switched the cluster.

References

Macnaughton-Smith, P., Williams, W.T., Dale, M.B., Mockett, L.G. (1964) "Dissimilarity Analysis: a new Technique of Hierarchical Sub-division", Nature, 202, 1034–1035.

Examples

data("Amount")
timeVariations = detectTimeVariations(data = Amount,
    value = "amount",
    item = "item",
    timestamp = "date",
    temporalAggregation = "week")