Forecasting call frequency at a financial services call centre

A forecasting model is developed for the number of daily applications for loans at a financial services telephone call centre. The purpose of the forecasts and the associated prediction intervals is to provide effective staffing policies within the call centre. The model building process is constrained by the availability of only 2 years and 7 months of data. The distinctive feature of the data is that demand is driven in the main by advertising. The analysis given focuses on applications stimulated by press advertising. Unlike previous analyses of broadly similar data, where ARIMA models were used, a model with a dynamic level, multiplicative calendar effects and a multiplicative advertising response is developed and shown to be effective.     

Recursive partition and amalgamation with the exponential family: Theory and applications

The theory of tree-growing (RECPAM approach) is developed for outcome variables which are distributed as the canonical exponential family. The general RECPAM approach (consisting of three steps: recursive partition, pruning and amalgamation), is reviewed. This is seen as constructing a partition with maximal information content about a parameter to be predicted, followed by simplification by the elimination of ‘negligible’ information. The measure of information is defined for an exponential family outcome as a deviance difference, and appropriate modifications of pruning and amalgamation rules are discussed. It is further shown how the proposed approach makes it possible to develop tree-growing for situations usually treated by generalized linear models (GLIM). In particular, Poisson and logistic regression can be tree-structured. Moreover, censored survival data can be treated, as in GLIM, by observing a formal equivalence of the likelihood under random censoring and an appropriate Poisson model. Three examples are given of application to Poisson, binary and censored survival data.     

关于(?)-拟微分核的连续性

Supposa that f(x) is a quasidifferentiable function, defined on S(?)R~n where S is an open set, with a -equivalent bounded quasidifferential subfam ily. Lenma I     

Quadratic data envelopment analysis

Data Envelopment Analysis (DEA) offers a piece-wise linear approximation of the production frontier. The approximation tends to be poor if the true frontier is not concave, eg in case of economies of scale or of specialisation. To improve the flexibility of the DEA frontier and to gain in empirical fit, we propose to extend DEA towards a more general piece-wise quadratic approximation, called Quadratic Data Envelopment Analysis (QDEA). We show that QDEA gives statistically consistent estimates for all production frontiers with bounded Hessian eigenvalues. Our Monte-Carlo simulations suggest that QDEA can substantially improve efficiency estimation in finite samples relative to standard DEA models.     

A STUDY OF VARIOUS BARRIERS IN ENCLOSED SOUND FIELD BY USING THE COMPUTER PROGRAM—SOFIS

In the study of the behaviors of barriers in an enclosed field, one should take into account such phenomena as sound energy reflection, absorption, scattering and diffraction. Therefore, the study is much more difficult than that in free field. In this paper, sound barriers are classified into four kinds according to their size, number and shape. Each kind of barriers is modelled by a corresponding method based on a computer program—SOFIS. The program combines the ray-tracing technique and statistical method. The impulse response and some acoustical parameters such as sound pressure level at different positions can be calculated by the program, no matter there are a certain kind of barriers in the field or the field is empty. The ray-tracing program and the algorithms for various barriers are validated by the comparison between measurement and prediction of the reverberation room and the anechoic room of the Northwestern Polytechnic University.     

A Language for Teaching Discrete-event Simulation

Courses which teach discrete-event simulation are based on many different simulation languages. The requirements for a language to support teaching simulation are discussed. In particular, it is recommended that such languages separate into distinct modules those aspects of simulation which are taught as separate topics. Implementation of the separation is discussed. The SEESIM language, developed as a teaching aid, is described, and examples of its use are given. Straightforward use of SEESIM can be learned quickly, yet the language provides facilities for a staged introduction to advanced concepts of simulation.     

Application of pressure sensitive paint measurement to a low-solidity cascade diffuser of a transonic centrifugal compressor

A pressure sensitive paint (PSP) measurement has been known as a pressure field measurement technique based on the oxygen quenching phenomenon of luminescence of specific luminophores. A PSP measurement was applied for pressure field measurement in a low-solidity circular cascade diffuser of a single-stage transonic centrifugal compressor with 5 in pressure ratio for HFC134a gas. The oxygen concentration was about 500 ppm. Ru (bath-phen) was adsorbed on a silica-gel thinlayer chromatography sheet, and the sheet was pasted onto the side-wall between the cascade vanes. A drastic change in luminescent intensity was recognized during a surge condition. Also the pressure variations based on luminescent intensity agreed well with the pressure fluctuations measured using a semiconductor pressure sensor with high-frequency-response. It was shown that a PSP measurement worked well to investigate the unsteady pressure fields in a circular cascade diffuser of a transonic centrifugal compressor. Moreover, the time response of PSP becomes clear as a problem to be overcome for the present.