Skip to main content

Table 8 Classification results using VAE-reduced 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

0.656

0.530

0.733

0.629

0.712

0.596

0.712

0.601

AKBNK

0.652

0.592

0.652

0.557

0.645

0.556

0.603

0.520

HALKB

0.569

0.542

0.613

0.546

0.615

0.549

0.588

0.525

ISCTR

0.621

0.535

0.663

0.549

0.680

0.556

0.654

0.534

SKBNK

0.685

0.610

0.737

0.595

0.726

0.564

0.722

0.576

TSKB

0.650

0.530

0.694

0.544

0.685

0.526

0.645

0.504

VAKBN

0.563

0.553

0.563

0.546

0.576

0.548

0.566

0.530

YKBNK

0.583

0.541

0.537

0.529

0.565

0.536

0.575

0.527

Average

0.622

0.554

0.649

0.562

0.651

0.554

0.633

0.540

  1. Bold numbers indicate the best performance