Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Offering a unifying theoretical perspective not readily available in any other text, this innovative guide to econometrics uses simple geometrical arguments to develop students' intuitive understanding of basic and advanced topics, emphasizing throughout the practical applications of modern theory and nonlinear techniques of estimation. One theme of the text is the use of artificial regressions for estimation, reference, and specification testing of nonlinear models, including diagnostic tests for parameter constancy, serial correlation, heteroscedasticity, and other types of mis-specification. Explaining how estimates can be obtained and tests can be carried out, the authors go beyond a mere algebraic description to one that can be easily translated into the commands of a standard econometric software package. Covering an unprecedented range of problems with a consistent emphasis on those that arise in applied work, this accessible and coherent guide to the most vital topics in econometrics today is indispensable for advanced students of econometrics and students of statistics interested in regression and related topics. It will also suit practising econometricians who want to update their skills. Flexibly designed to accommodate a variety of course levels, it offers both complete coverage of the basic material and separate chapters on areas of specialized interest.

Estimation and Inference in Econometrics

In this book, Andrew Harvey sets out to provide a unified and comprehensive theory of structural time series models. Unlike the traditional ARIMA models, structural time series models consist explicitly of unobserved components, such as trends and seasonals, which have a direct interpretation. As a result the model selection methodology associated with structural models is much closer to econometric methodology. The link with econometrics is made even closer by the natural way in which the models can be extended to include explanatory variables and to cope with multivariate time series. From the technical point of view, state space models and the Kalman filter play a key role in the statistical treatment of structural time series models. The book includes a detailed treatment of the Kalman filter. This technique was originally developed in control engineering, but is becoming increasingly important in fields such as economics and operations research. This book is concerned primarily with modelling economic and social time series, and with addressing the special problems which the treatment of such series poses. The properties of the models and the methodological techniques used to select them are illustrated with various applications. These range from the modellling of trends and cycles in US macroeconomic time series to to an evaluation of the effects of seat belt legislation in the UK.

Forecasting, Structural Time Series Models and the Kalman Filter

The author systematically examines one of the important issues of information — establishing the market price. He introduces the concept of «search» — where a buyer wanting to get a better price, is forced to question sellers. The article deals with various aspects of finding the necessary information.

Economics of Information

Credit scoring models are very important tools for credit granting institutions to assess the credit risk of their customers. Most previous researches focus on improving predictive accuracy of models. In this research, a weighted LS-SVM credit scoring model with Area under ROC curve maximization is proposed and optimized by direct search. The tests on two real-world datasets show that it is effective for building the credit scoring model with good AUC performance.

Weighted LS-SVM Credit Scoring Models with AUC Maximization by Direct Search

This article presents a robust optimization formulation for dealing with production cost uncertainty in an oligopolistic market scenario. It is not uncommon that players in the market face an equilibrium selling price but uncertain production costs. We show that, based on a nominal problem, the robust optimization formulation can be derived as a variational inequality with control and state variables. This convenient approach may be applied for computing optimal solutions efficiently, which help manufacturers dramatically and rapidly reform production and distribution schedules such that they can compete in the market successfully.

A robust optimization model for dynamic market with uncertain production cost

Due to incomplete knowledge and information, it is not enough to use precise mathematics to model a complex system. In order to represent the vagueness in everyday life, Zadeh introduced the concept of fuzzy sets in 1965. Based on this concept, Bellman and Zadeh presented the fuzzy decision theory. They defined decision-making in a fuzzy environment with a decision set which unifies a fuzzy objective and a fuzzy constraint. Suppose that fuzzy sets are defined on a set of alternatives, X. Let the fuzzy set for the fuzzy objective be identified as G, the fuzzy set for the constraints as C, and let decision set D be a unifying factor between G and C. Then, decision set D can be defined as an intersection set between fuzzy objective G and fuzzy constraint C, D = G ∩ C. Decision set D is a fuzzy set, named a fuzzy decision. The corresponding membership function of the decision set D is given by:

Fuzzy Decision Making and Maximization Decision Making

Different from traditional tax audit, supervision with self-audit is a combination of audit by the taxpayer himself and audit by the tax authority. This paper mainly studies a taxpayer’s optimal policy of tax evasion under supervision with self-audit and its related properties, in order to deduce some effective suggestions and theoretical bases to restrain tax evasion. Assuming that only a certain proportion of evaded tax can be discovered when the audit is executed, the authors first formulate a static model with self-audit. This model is divided into two stages. At the first stage, taxpayers declare their taxes, then the tax authority chooses audit objects, based on a known probability, and announces the result; if the taxpayer is chosen, he will enter the second stage, during which he has a chance to pay the evaded tax and the corresponding late fees and then is audited by the tax authority. The authors show the existence and uniqueness of the optimal amount of tax evasion at the first stage and the optimal proportion to self-expose at the second stage. The authors also discuss the related properties of the interior solution, and do elasticity analyses on some parameters. Besides, the authors extend the static model into the corresponding two-period model, and study the existence and uniqueness of the solution of the extended model. Finally, under the assumption that tax evasion can only be discovered with a certain probability when the audit is executed, the authors formulate another static model with self-audit and investigate its properties.

Tax Evasion: Models with Self-Audit

Aimed at the problem of occasional congestion control, the cusp catastrophe theory is used to establish the catastrophe model of the urban road system under occasional congestion, finding breakpoints and analyzing stability after urban road system catastrophes by constructing the energetic function; based on the catastrophe characteristics of the urban road system, the feasibility method of congestion control is discussed. The results show that the control method of traffic flow based on catastrophe characteristics of the urban road system can effectively improve the efficiency of the road system in theory. Finally, the applicability of the control method based on catastrophe characteristics is analyzed by examples under different occasional congestion situations.

/pdf/research-on-the-traffic-flow-control-of-urban-occasional-1dg75ux2sh.pdf

Kin Keung Lai

Papers

Weighted LS-SVM Credit Scoring Models with AUC Maximization by Direct Search

A robust optimization model for dynamic market with uncertain production cost

Fuzzy Decision Making and Maximization Decision Making

Tax Evasion: Models with Self-Audit

Research on the Traffic Flow Control of Urban Occasional Congestion Based on Catastrophe Theory