FACTMAC Procedure

PROC FACTMAC Statement

PROC FACTMAC <options>;

The PROC FACTMAC statement invokes the procedure. Table 1 summarizes the options available in this statement.

Table 1: PROC FACTMAC Statement Options

Option	Description
Input Data Table Options
DATA=	Specifies the input data table
Factorization Options
APPLYROWORDER	Specifies that the procedure use a prespecified data distribution
LEARNSTEP=	Specifies the learning step size for the SGD algorithm
MAXITER=	Specifies the maximum number of iterations
NFACTORS=	Specifies the number of factors to estimate for the model
NONNEGATIVE	Requests nonnegative factorization
NTHREADS=	Specifies the number of threads to use on each computation node
OUTMODEL=	Specifies the output model data table to contain the computed factor parameters
SEED=	Specifies the seed to be used for pseudorandom number generation
Output Options
NOPRINT=	Suppresses ODS output

You can specify the following options:

APPLYROWORDER

uses a data distribution and row order as determined by a previous partition action call. For more information, see the section The APPLYROWORDER Option in Chapter 2, Shared Concepts.

DATA=libref.data-table

names the input data table for PROC FACTMAC to use. The default is the most recently created data table. libref.data-table is a two-level name, where

libref: refers to a collection of information that is defined in the LIBNAME statement and includes the library, which includes a path to the data, and a session identifier, which defaults to the active session but which can be explicitly defined in the LIBNAME statement. For more information about libref, see the section Using CAS Sessions and CAS Engine Librefs.
data-table: specifies the name of the input data table.

LEARNSTEP=number

specifies the learning step size for the stochastic gradient descent (SGD) algorithm, where number is a positive real number. The learning step size controls the amount by which the factors are updated at each iteration.

By default, LEARNSTEP=0.001. This value can be tuned with the AUTOTUNE statement.

MAXITER=number

specifies the maximum number of iterations for the algorithm to perform, where number is an integer greater than or equal to 1. In each iteration of the SGD method, the factors are recomputed.

By default, MAXITER=1. This value can be tuned with the AUTOTUNE statement.

NFACTORS=number

specifies the number of factors to estimate for the model, where number is an integer greater than or equal to 1.

By default, NFACTORS=1. This value can be tuned with the AUTOTUNE statement.

NONNEGATIVE

performs nonnegative factorization, in which the estimated factors are greater than or equal to 0 and the estimated biases are 0.

By default, nonnegative factorization is not performed.

NOPRINT

suppresses ODS output.

NTHREADS=number-of-threads

specifies the number of threads to use for the computation, where number-of-threads is an integer from 1 to 64, inclusive. The default value is the maximum number of available threads per computer.

OUTMODEL=libref.data-table

specifies the output model data table to contain the computed factor parameters. libref.data-table is a two-level name, where libref refers to the library, and data-table specifies the name of the output data table. For more information about this two-level name, see the DATA= option and the section Using CAS Sessions and CAS Engine Librefs.

SEED=random-seed

specifies an integer that is used to start the pseudorandom number generator. This option enables you to reproduce the same sample output, but only when NTHREADS=1. If you do not specify a seed or you specify a value less than or equal to 0, the seed is generated from reading the time of day from the computer’s clock.

By default, SEED=0.

Last updated: September 04, 2026