Skip to main content

Table 3 Matrix factorization models ((3) and (4)) used in numerical experiments

From: Matrix factorization for the reconstruction of cervical cancer screening histories and prediction of future screening results

Model name

\({R}\)

\(W_{n, t} : (n, t) \in \Omega\)

\(\max z_n\) (years)

Matrix Factorization (MF)

\({{D}}\)

1

Convolutional MF (CMF)

\({{K}}{{D}}\)

1

Shifted CMF (SCMF)

\({{K}}{{D}}\)

1

3

Weighted CMF (WCMF)

\({{K}}{{D}}\)

\({\widehat{p}}(s \mid \epsilon ) \, / \, {\widehat{p}}((n, t) \in \Omega )\)

Shifted WCMF (SWCMF)

\({{K}}{{D}}\)

\({\widehat{p}}(s \mid \epsilon ) \, / \, {\widehat{p}}((n, t) \in \Omega )\)

3