Personalized web services strive to adapt their services (advertisements, news articles, etc.) to individual users by making use of both content and user information. Despite a few recent advances, this problem remains challenging for at least two reasons. First, web service is featured with dynamically changing pools of content, rendering traditional collaborative filtering methods inapplicable. Second, the scale of most web services of practical interest calls for solutions that are both fast in learning and computation.In this work, we model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks.The contributions of this work are three-fold. First, we propose a new, general contextual bandit algorithm that is computationally efficient and well motivated from learning theory. Second, we argue that any bandit algorithm can be reliably evaluated offline using previously recorded random traffic. Finally, using this offline evaluation method, we successfully applied our new algorithm to a Yahoo! Front Page Today Module dataset containing over 33 million events. Results showed a 12.5% click lift compared to a standard context-free bandit algorithm, and the advantage becomes even greater when data gets more scarce.

/pdf/a-contextual-bandit-approach-to-personalized-news-article-13tixfy0pk.pdf

A contextual-bandit approach to personalized news article recommendation

The integration of GIS and multicriteria decision analysis has attracted significant interest over the last 15 years or so This paper surveys the GIS‐based multicriteria decision analysis (GIS‐MCDA) approaches using a literature review and classification of articles from 1990 to 2004 An electronic search indicated that over 300 articles appeared in refereed journals The paper provides taxonomy of those articles and identifies trends and developments in GIS‐MCDA

https://www.tandfonline.com/doi/pdf/10.1080/13658810600661508

GIS‐based multicriteria decision analysis: a survey of the literature

PROMETHEE: A comprehensive literature review on methodologies and applications

https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1766&context=agronomyfacpub

Yield gap analysis with local to global relevance—A review

Agricultural systems models worldwide are increasingly being used to explore options and solutions for the food security, climate change adaptation and mitigation and carbon trading problem domains. APSIM (Agricultural Production Systems sIMulator) is one such model that continues to be applied and adapted to this challenging research agenda. From its inception twenty years ago, APSIM has evolved into a framework containing many of the key models required to explore changes in agricultural landscapes with capability ranging from simulation of gene expression through to multi-field farms and beyond.Keating et?al. (2003) described many of the fundamental attributes of APSIM in detail. Much has changed in the last decade, and the APSIM community has been exploring novel scientific domains and utilising software developments in social media, web and mobile applications to provide simulation tools adapted to new demands.This paper updates the earlier work by Keating et?al. (2003) and chronicles the changing external challenges and opportunities being placed on APSIM during the last decade. It also explores and discusses how APSIM has been evolving to a "next generation" framework with improved features and capabilities that allow its use in many diverse topics. APSIM is an agricultural modelling framework used extensively worldwide.It can simulate a wide range of agricultural systems.It begins its third decade evolving into an agro-ecosystem framework.

APSIM - Evolution towards a new generation of agricultural systems simulation

Implementation of the analytical hierarchy process with VBA in ArcGIS

Improving geological models using a combined ordinary–indicator kriging approach

Quantifying yield gaps in rainfed cropping systems: A case study of wheat in Australia

PROMETHEE is a well known multicriteria decision support method which gives insight into the preference structure of a whole set of alternatives. The retrieved preference information is used to give the partial or complete preorder of the available alternatives which makes PROMETHEE a well suited decision support tool if a ranking of available alternatives is desired. A relatively low degree of mathematical complexity makes PROMETHEE an attractive method for all non experts involved in a decision process. This paper discusses the integration of PROMETHEE in a GIS. It will be shown how the combination of a sophisticated decision support methodology with powerful spatial analysis and visualisation capabilities can be applied to evaluating decision alternatives that are made up of regular or irregular shaped zones of raster cells. Deterministic as well as stochastic PROMETHEE approaches are considered and general recommendations on the use of stochastic simulation methods are given. Moreover, a framework is presented which facilitates the application of the proposed approaches.

Oswald Marinoni

Papers

Implementation of the analytical hierarchy process with VBA in ArcGIS

Improving geological models using a combined ordinary–indicator kriging approach

Quantifying yield gaps in rainfed cropping systems: A case study of wheat in Australia

A stochastic spatial decision support system based on PROMETHEE

Precipitation influences pathogenic bacteria and antibiotic resistance gene abundance in storm drain outfalls in coastal sub-tropical waters.