Skip to main content

Table 7 Classification results using own stock features

From: An efficient stock market prediction model using hybrid feature reduction method based on variational autoencoders and recursive feature elimination

Stocks

LSTM (basic)

LSTM (with attention)

SVM

LightGBM

Acc

F-Mea

Acc

F-Mea

Acc

F-Mea

Acc

F-Mea

ALBRK

0.704

0.642

0.737

0.668

0.691

0.661

0.711

0.669

AKBNK

0.625

0.537

0.621

0.554

0.585

0.551

0.598

0.539

HALKB

0.569

0.542

0.629

0.595

0.568

0.557

0.578

0.553

ISCTR

0.629

0.573

0.668

0.574

0.646

0.564

0.622

0.548

SKBNK

0.674

0.602

0.744

0.653

0.693

0.649

0.713

0.629

TSKB

0.666

0.593

0.688

0.609

0.611

0.586

0.681

0.562

VAKBN

0.552

0.545

0.567

0.549

0.575

0.557

0.562

0.543

YKBNK

0.615

0.556

0.609

0.585

0.587

0.556

0.585

0.558

Average

0.629

0.574

0.658

0.598

0.620

0.585

0.631

0.575

  1. Bold numbers indicate the best performance