Table 2 Classification performance for Shifted Weighted Convolutional Matrix Factorization over varying forecast horizon as the probability of agreement [13] score (\(\Phi _s\) from 8) with \(95 \%\) CI

0.5

\(0.35 \left[ 0.26, 0.40 \right]\)

\(0.61 \left[ 0.52, 0.63 \right]\)

\(0.21 \left[ 0.18, 0.24 \right]\)

\(0.91 \left[ 0.86, 0.95 \right]\)

2.1

1

\(0.32 \left[ 0.25, 0.36 \right]\)

\(0.59 \left[ 0.56, 0.62 \right]\)

\(0.45 \left[ 0.35, 0.52 \right]\)

\(0.90 \left[ 0.83, 0.96 \right]\)

2.3

2

\(0.36 \left[ 0.29, 0.41 \right]\)

\(0.50 \left[ 0.47, 0.51 \right]\)

\(0.33 \left[ 0.24, 0.41 \right]\)

\(0.86 \left[ 0.80, 0.90 \right]\)

2.1

3

\(0.38 \left[ 0.33, 0.43 \right]\)

\(0.40 \left[ 0.38, 0.41 \right]\)

\(0.24 \left[ 0.21, 0.26 \right]\)

\(0.79 \left[ 0.70, 0.85 \right]\)

1.8

5

\(0.20 \left[ 0.086, 0.29 \right]\)

\(0.024 \left[ 0.020, 0.025 \right]\)

\(0.20 \left[ 0.10, 0.28 \right]\)

\(0.68 \left[ 0.66, 0.73 \right]\)

1.1