Market Model Benchmark Suite for Machine Learning Techniques

Prause, Martin; Weigand, Jürgen

doi:10.1109/mci.2018.2866726

Cited by 4 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benefit of this algorithm is that it can cluster the data set without making too many assumptions, resulting in more accurate and stable clustering results. Martin Prause [8] and others proposed a benchmark trade model suite for testing machine learning algorithms and decision simulation. This model benchmark suite is capable of simulating a particular economic market environment, which includes numerous enterprises with distinct strategies and a complex decision-making and product trading procedure.…”

Section: Related Workmentioning

confidence: 99%

Optimization Analysis of Business Circle Based on Machine Learning

Fang

2023

HSET

View full text Add to dashboard Cite

This paper begins with a discussion of data preprocessing in order to improve the data quality, standardize the feature ratio, and comprehend the data pattern and trend. The preprocessing technology utilized in this paper is feature aggregation, which aggregates the transaction data based on the transaction time and date to determine the transaction type (weekday or weekend) and calculates the transaction frequency and average amount for each store as the final feature of cluster analysis. Then, for the processed data, this paper compares the advantages and disadvantages of three different clustering algorithms, including K-means clustering, spectral clustering, and DEC deep clustering, in terms of their clustering effects. The conclusion of the paper is that deep clustering is superior to traditional clustering algorithms in terms of clustering precision, but it requires more computing resources and offers practical suggestions for existing shop clustering.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimization Analysis of Business Circle Based on Machine Learning

Fang

2023

HSET

View full text Add to dashboard Cite

show abstract

“…It is known, that the up-to-date artificial intelligence research and technology uses deep machine learning algorithms, which improves quality of modern business processes in the areas of logistics management, optimize supply planning, financial operations, production processes, predict risks, increase customer satisfaction, diagnose diseases, selects dosages of drugs and solve other narrow classification problems, as well as the creation of a strong artificial intelligence, universal in application to various tasks [1][2][3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Interpretation of a trained neural network based on genetic algorithms

Pimenov

2020

ICS

View full text Add to dashboard Cite

Introduction: Artificial intelligence development strategy involves the use of deep machine learning algorithms in order to solve various problems. Neural network models trained on specific data sets are difficult to interpret, which is due to the “black box” approach when knowledge is formed as a set of interneuronal connection weights. Purpose: Development of a discrete knowledge model which explicitly represents information processing patterns encoded by connections between neurons. Methods: Adaptive quantization of a feature space using a genetic algorithm, and construction of a discrete model for a multidimensional OLAP cube with binary measures. Results: A genetic algorithm extracts a discrete knowledge carrier from a trained neural network. An individual's chromosome encodes a combination of values of all quantization levels for the measurable object properties. The head gene group defines the feature space structure, while the other genes are responsible for setting up the quantization of a multidimensional space, where each gene is responsible for one quantization threshold for a given variable. A discrete model of a multidimensional OLAP cube with binary measures explicitly represents the relationships between combinations of object feature values and classes. Practical relevance: For neural network prediction models based on a training sample, genetic algorithms make it possible to find the effective value of the feature space volume for the combinations of input feature values not represented in the training sample whose volume is usually limited. The proposed discrete model builds unique images of each class based on rectangular maps which use a mesh structure of gradations. The maps reflect the most significant integral indicators of classes that determine the location and size of a class in a multidimensional space. Based on a convolution of the constructed class images, a complete system of production decision rules is recorded for the preset feature gradations.

show abstract

“…Interestingly, it seems that the same act of academic publication may interfere with the price of the shares [2]. These facts, together with the availability of new data sources [21], [24], markets [18], [25], financial instruments [8] and algorithms [20], [22] make the predictability of stock returns a hot topic [33].…”

Section: Introductionmentioning

confidence: 99%

On the Economic Significance of Stock Market Prediction and the No Free Lunch Theorem

Bousoño-Calzón

Bustarviejo-Munoz

Aceituno³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Forecasting of stock market returns is a challenging research activity that is now expanding with the availability of new data sources, markets, financial instruments, and algorithms. At its core, the predictability of prices still raises important questions. Here, we discuss the economic significance of the prediction accuracy. To develop this question, we collect the daily series prices of almost half of the publicly traded companies around the world over a period of ten years and formulate some trading strategies based on their prediction. Proper visualization of these data together with the use of the No Free Lunch theoretical framework gives some unexpected results that show how the a priori less accurate algorithms and inefficient strategies can offer better results than the a priori best alternatives in some particular subsets of data that have a clear interpretation in terms of economic sectors and regions.

show abstract

Market Model Benchmark Suite for Machine Learning Techniques

Cited by 4 publications

References 32 publications

Optimization Analysis of Business Circle Based on Machine Learning

Optimization Analysis of Business Circle Based on Machine Learning

Interpretation of a trained neural network based on genetic algorithms

On the Economic Significance of Stock Market Prediction and the No Free Lunch Theorem

Contact Info

Product

Resources

About