Improving Predictive Models with Expert Knowledge
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".
Deadline for manuscript submissions: closed (30 October 2022) | Viewed by 29730
Special Issue Editor
Interests: asymptotic and nonparametric statistics; multivariate analysis; resampling and statistical/machine learning in theory and practice; survival and time series analysis
Special Issue Information
Dear Colleagues,
Big Data has changed many aspects of present-day statistics: In many fields, predictive models are developed in a purely data-driven way, often even using the directive 'the more data the better', building on Peter Norvig’s quote 'We don’t have better algorithms. We just have more data.' However, the success of Google and Amazon is not one-to-one transferable to other areas. In fact, Big Data is not equal to good data, and for most applications in sciences or industry, accurate and reasonable predictions require additional insights. This expert or domain knowledge may be given by simple physical constraints of the output or knowledge about underlying relations, dependencies, or causalities. Unfortunately, there are not many studies on methods for the inclusion of expert knowledge, let alone its (information and predictive) effect. This is where the current Issue proposal kicks in, for which we envision systematic studies (simulation and theory) on this topic covering application areas from natural science models to industrial time series forecasting. For example, we envision studies that analyze and quantify the improvement of additional information for machine-learning methods in terms of entropy or other information-theoretic, information-quality, or importance measures. Other potential examples may cover the influence of the chosen experimental design, the connection to AutoML, missings, penalization, and distributional discrepancies (e.g., measured via Kullback–Leibler), etc.
Prof. Dr. Markus Pauly
Guest Editor
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- classification
- deep learning
- domain knowledge
- feature engineering
- information gain
- machine learning
- regression
- regularization
- statistical learning
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.
Further information on MDPI's Special Issue policies can be found here.