TAILIEUCHUNG - Developing a volume forecasting model

This study builds a series of models to predict trading volume in European markets using different statistical methods. The analysis considers a number of aspects, such as special events (. MSCI rebalances, futures expiries, or cross-market holidays), day-of-the-week effects, and the volume-price relation asymmetry, in order to perform contextual one-step ahead prediction. We investigate the prediction error for each calendar circumstance to infer a cross-stock event-oriented switching model for volume prediction. The study concludes by proposing a stock-specific out-of-sample meta model that is fit by selecting an initial stock-specific model yielding the best performance for the most recent observations. | Journal of Applied Finance Banking vol. 7 no. 1 2017 1-40 ISSN 1792-6580 print version 1792-6599 online Scienpress Ltd 2017 Developing a Volume Forecasting Model Bogdan Batrinca1 Christian W. Hesse2 and Philip C. Treleaven3 Abstract This study builds a series of models to predict trading volume in European markets using different statistical methods. The analysis considers a number of aspects such as special events . MSCI rebalances futures expiries or cross-market holidays day-of-the-week effects and the volume-price relation asymmetry in order to perform contextual one-step ahead prediction. We investigate the prediction error for each calendar circumstance to infer a cross-stock event-oriented switching model for volume prediction. The study concludes by proposing a stock-specific out-of-sample metamodel that is fit by selecting an initial stock-specific model yielding the best performance for the most recent observations. JEL classification numbers C32 C52 C53 G14 G15 Keywords Trading volume expiry day effect holiday effect behavioral finance European stock market feature selection 1 Introduction Measuring trading performance is a challenging research area but there are certain factors that have a clear influence on the overall trading performance such as the market impact which is the effect caused by a market participant who buys or sells shares consisting in the extent to which the price goes upward for a buy order or downward for a sell order. The market impact cost is defined as the difference between the actual price and the hypothetical price provided that the order was not created 1 . Market impact can move the prices adversely leading to decreased profits or turning profitable strategies into losing strategies. 1Department of Computer Science University College London Gower Street London WC1E 6BT UK. department of Computer Science University College London Gower Street London WC1E 6BT UK. department of Computer Science University College London .

• Đầu tư Chứng khoán
• Volume forecasting model
• Trading volume
• Expiry day effect
• Holiday effect
• Behavioral finance
• European stock market
• Feature selection
• Compositional data
• Beta distribution
• Variable selection
• Correlation based feature selection
• Recursive partitioning
• Chromatography data
• A Progressive Feature
• Selection Algorithm
• Ultra Large Feature Spaces
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Data mining
• Heart Disease Prediction
• Infinite Latent Feature Selection
• HD symptoms
• International Journal of Computer Science & Communication Networks
• Clustering based feature selection and outlier analysis
• Feature selection and outlier analysis
• Find feasible clustering algorithms
• Intrusion detection techniques
• DNA methylation
• While feature selection
• Illumina Infinium methylation
• Cancer diagnosis
• BMC Bioinformatics
• Feature cost
• Genetic algorithm
• Budget constraint
• Cost limit
• Information sciences
• Dimensionality reduction
• High dimensional feature selection
• Protein structure
• A protein structure consists
• Previous feature selection methods
• Protein classification dataset
• Feature ranking methods
• Classification algorithms
• Classification accuracy
• Naive Bayes
• RBF network
• BMC Cancer
• Drug sensitivity prediction
• Recursive feature elimination
• Cancer Genome Project
• Feature interaction
• Filter method
• Biological data
• Alignment free
• Sequence feature
• Support vector machine
• Credit scoring
• Local search
• Stochastic local search
• Variable neighborhood search
• Discriminative motif
• Hepatitis C virus
• Sequential forward floating selection
• Semi supervised feature selection
• Predict HCV treatment
• Gene selection
• Machine learning
• Wrapper methods
• Joint Feature Selection
• Distributed Stochastic Learning
• Large Scale Discriminative Training in SMT
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• A Framework of Feature Selection Methods
• Text Categorization
• Shoushan Li
• Transfer Learning
• Word Sense Disambguation
• Word Clustering
• Word Selection based Feature Reduction
• MaxEnt based Hindi NER
• Convolution Kernels
• Natural Language Processing Tasks
• Learning Word Senses
• Order Identification Capabilities
• A New Feature Selection Score
• Multinomial Naive Bayes Text Classification
• KL Divergence
• Hedge algebras
• Fuzzy classification system
• High dimensional dataset
• High dimensional datasets
• The fuzzy rule based classifier design
• Journal of Computer Science and Cybernetics
• Automatic heart disease prediction
• Feature selection and data mining technique
• Automatic Heart Disease
• The patients dataset
• Context aware fitness functions
• Genetic Programming
• Graph patterns
• TTSP graphs