Filters








95,025 Hits in 5.1 sec

Using a Financial Training Criterion Rather than a Prediction Criterion

Yoshua Bengio
1997 International Journal of Neural Systems  
The traditional approach is to train a model using a prediction criterion, such as minimizing the squared error between predictions and actual values of a dependent variable, or maximizing the likelihood  ...  We nd here with noisy time-series that better results can be obtained when the model is directly trained in order to maximize the nancial criterion of interest, here gains and losses (including those due  ...  Ghosn, for their useful comments, as well as, the NSERC, FCAR, IRIS Canadian funding agencies for support.  ... 
doi:10.1142/s0129065797000422 fatcat:lbwanqafbvhkviuakrpixgvzvi

A re-evaluation of auditors' opinions versus statistical models in bankruptcy prediction

Lili Sun
2006 Review of Quantitative Finance and Accounting  
I thank the Whitcomb Center for Research in Financial Services for providing research support through use of the WRDS system.  ...  The prediction ability of the hazard model with incorporation of non-financial-ratio variables is superior to that of auditors' going concern opinions in the holdout sample.  ...  Use these with all (344) bankrupt firm-years in the training sample to form a training resample.  ... 
doi:10.1007/s11156-006-0003-x fatcat:vh67tuoosravvbkeyxjvzaijeq

The Life History Questionnaire as a predictor of performance in Navy diver training

R Helmreich, R Bakeman, R Radloff
1973 Journal of Applied Psychology  
. ;0 T I I t The Life History Questionnaire: Prediction of Performance in Navy Diver Training t FS C In It T I v r N 0T E~ S (7'pe ,it rIeIiett a~nti. On, lien 0 e .lah .)  ...  #in rý f Nimnt"" I ,n t r cniternd whiter fhr 4,wrrfIl *rp,)r8 to Ir sf .s b d, <(11 k, I t9,A 7 IN(.  ...  in diver training suggests that the LHQ may be a highly useful tool.  ... 
pmid:4784758 fatcat:hcpxvvmo4ra7nd57vka74jknri

Non-linear discriminant feature extraction using generalized back-propagation network

Jian-Hui Jiang, Ji-Hong Wang, Xia Chu, Ru-Qin Yu
1996 Journal of Chemometrics  
In discriminant analysis the classification results are always more strongly governed by the value of a suitably selected discriminant criterion rather than by the mean-square error.  ...  In contrast, to maximize the discriminant criterion (1), the network outputs can be scattered into a two-dimensional feature space rather than a narrow line during the intermediate learning process, which  ... 
doi:10.1002/(sici)1099-128x(199607)10:4<281::aid-cem417>3.0.co;2-d fatcat:usnzkujctfcpzcyxfgttahdjua

A Comparison of Model Selection Procedures for Predicting Turning Points in Financial Time Series [chapter]

Thorsten Poddig, Claus Huber
1999 Lecture Notes in Computer Science  
Our results indicate that there are no differences in the predictive quality when alternative model selection criteria are used.  ...  The aim of this paper is to compare the influence of different model selection criteria on the performance of ARMA-and VAR-models to predict turning points in nine financial time series.  ...  A performance criterion in this spirit is the Cumulative Wealth (CW ). We predict TPs in nine financial time series of monthly periodicity with ARMA-and VAR-models using rolling regressions.  ... 
doi:10.1007/978-3-540-48247-5_63 fatcat:4auuej6xyvas5ci6t2iddc3lzy

Low-cost wind resource assessment for small-scale turbine installations using site pre-screening and short-term wind measurements

Shemaiah Matthias Weekes, Alison S. Tomlin
2014 IET Renewable Power Generation  
criterion.  ...  In stage one, sites were pre-screened using a boundary layer scaling model to predict the mean wind power density, including estimated uncertainties, and these predictions were compared to a minimum viability  ...  Acknowledgements This work was financially supported by the Engineering and Physical Sciences Research Council through the Doctoral Training Centre in Low Carbon Technologies.  ... 
doi:10.1049/iet-rpg.2013.0152 fatcat:3qpsurq6yff6xlmmnp75ftjgza

Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy

Philippe du Jardin
2010 Neurocomputing  
used to design models is a key factor in performance.  ...  As a result, we demonstrate that a search strategy cannot be designed without considering the characteristics of the modeling technique and that the fit between the variable selection method and the technique  ...  With all these criteria, we used only a backward search rather than a forward or a stepwise search.  ... 
doi:10.1016/j.neucom.2009.11.034 fatcat:4el43sd5szacdcfq5mgas6sb6m

Page 472 of The American Psychologist Vol. 15, Issue 7 [page]

1960 The American Psychologist  
Prefer- ence of employees for intrinsic rather than extrinsic, and financial over fringe benefits, are indicated.  ...  Psychologists committed a “leniency error.” Predictions of failure proved to be higher than chance, while the actual successes were predicted more often than chance.  ... 

Factors that Influence the Financial Literacy among Engineering Students

Binoy Thomas, P. Subhashree
2020 Procedia Computer Science  
Engineers of tomorrow have to be job-providers rather than job-seekers.  ...  Abstract Engineers of tomorrow have to be job-providers rather than job-seekers.  ...  to maximise those opportunities [3] , [4] . 1 Engineers of tomorrow have to be job-providers (entrepreneurs) rather than job-seekers.  ... 
doi:10.1016/j.procs.2020.05.161 fatcat:heghmlnj2fgstjkmanov4txtn4

Motivated Perspective Taking: Why Prompting Auditors to Take an Investor's Perspective Makes Them Treat Identified Audit Differences as Less Material†

Elizabeth C. Altiero, Yoon Ju Kang, Mark E. Peecher
2021 Contemporary Accounting Research  
criterion-by breaking or not breaking a favorable profitability trend.  ...  Investor-prompted auditors assess audit differences as less likely to be material than do unprompted auditors, but only when the qualitative criterion is not violated.  ...  We test our prediction in Study 1 using an experiment that manipulates a qualitative criterion and perspective taking, using audit seniors as participants.  ... 
doi:10.1111/1911-3846.12721 fatcat:x6lhdfwypvakzk2bvkv2ez2whm

OPELM and OPKNN in long-term prediction of time series using projected input data

Dušan Sovilj, Antti Sorjamaa, Qi Yu, Yoan Miche, Eric Séverin
2010 Neurocomputing  
In order to make accurate predictions, this paper presents a methodology that uses input processing before building the model.  ...  Long-term time series prediction is a difficult task.  ...  It is mainly an extension of the Least Angle Regression (LARS) algorithm [31] and hence, it is actually a variable ranking technique, rather than a selection one.  ... 
doi:10.1016/j.neucom.2009.11.033 fatcat:74gpxkxavramnbu7kodmqy6o7a

Page 14 of The American Psychologist Vol. 3, Issue 1 [page]

1948 The American Psychologist  
Also included in the “financial” category are those who decided to keep a high-paying job rather than enter into rehabilitation training.  ...  It seems probable that in all seven cases the training situation may have been at fault, rather than the vocational objective, assuming that the veterans were employable at all.  ... 

A MULTIPLE CRITERIA SORTING METHODOLOGY WITH MULTIPLE CLASSIFI CATION CRITERIA AND AN APPLICATION TO COUNTRY RISK EVALUATION

Aydin Ulucan, Kazim Baris Atici
2013 Technological and Economic Development of Economy  
Moreover, we test the classification ability of the standard UTADIS methodology using the out-of-classification criterion approach, a new variant of the studies comprising out-of-time and out-of-sample  ...  These results emphasize both the sensitivity of UTADIS models to the classification criteria and the importance of using a multiple classification criteria approach.  ...  Similarly, in out-of-time testing, UtADiS model is run using a set of alternatives (training sample) for a certain time period.  ... 
doi:10.3846/20294913.2012.763070 fatcat:nnsv5iwdhvd3nbadyerr6v3jyi

A Systematic Comparison of Training Criteria for Statistical Machine Translation

Richard Zens, Sasa Hasan, Hermann Ney
2007 Conference on Empirical Methods in Natural Language Processing  
We address the problem of training the free parameters of a statistical machine translation system.  ...  We show significant improvements over a state-of-the-art minimum error rate training baseline on a large Chinese-English translation task.  ...  The sentence-level MLE criterion does not distinguish these cases and is therefore a rather harsh training criterion.  ... 
dblp:conf/emnlp/ZensHN07 fatcat:floym4cvgfgbfoeytptdez2cve

Assessment Center Dimensions Predict Performance-Based Bonus in Business Management Settings

Leehu Zysberg
2012 Psychology  
validity using a performance criterion often unavailable to researchers-performance-based bonus payment.  ...  A series of ACs specially designed for the selection of candidates for entry-mid tier management positions in a large financial corporate (n = 180) was used as the sampling frame.  ...  The factors pertained to skill type (cognitive vs. interpersonal) rather than task type.  ... 
doi:10.4236/psych.2012.36071 fatcat:hujotthbmbhhvcozp2kuer2t64
« Previous Showing results 1 — 15 out of 95,025 results