Skip to main content

Table 11 Classification results using allstock_VAE 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

0.737

0.656

0.741

0.653

0.741

0.623

0.735

0.617

AKBNK

0.626

0.558

0.667

0.567

0.643

0.541

0.635

0.537

HALKB

0.579

0.563

0.660

0.562

0.619

0.555

0.613

0.555

ISCTR

0.678

0.554

0.657

0.575

0.660

0.567

0.651

0.557

SKBNK

0.749

0.633

0.750

0.624

0.743

0.580

0.746

0.581

TSKB

0.664

0.576

0.705

0.580

0.680

0.538

0.677

0.537

VAKBN

0.569

0.549

0.603

0.555

0.589

0.545

0.580

0.536

YKBNK

0.577

0.554

0.628

0.564

0.623

0.575

0.618

0.573

Average

0.647

0.580

0.676

0.585

0.662

0.566

0.657

0.562

  1. Bold numbers indicate the best performance