Adam Ghandar

There are many pressures on the global food system such as urbanization, climate change, and environmental degradation. Urban agriculture is an approach to producing food inside cities where, globally, more than half the worlds population live. It has been shown to have a range of potential benefits, for instance in reducing waste and logistics costs. Increased uptake of urban farming can even relieve pressure on the natural environment by reducing the burden of production required from farmland by creating space for it to recover from accumulated damage as a result of the use of unsustainable farming practices historically. This article describes an approach for a new type of decision support system suitable for urban farming production. We discuss differences between the requirements and the users of decision support in urban agriculture, and those of ordinary agribusiness enterprises. A case study is performed using a novel technology for urban farming: a cyber-physical implementation of aquaponics is enhanced with adaptive capabilities using a digital twin system and machine learning. Aquaponics is a farming technique that utilizes a harmonious nutrient exchange cycle for growing plants and fish together, while conserving water, and possibly without the need for soil or even sunlight. Empirical results are provided that evaluate the use of data driven decision analytics and a digital twin model to plan production from the aquaponic system during a three month trial. Another set of results evaluate a proposed modelling framework for large scale urban agriculture ecosystems. This concept forms the basis of the suggested approach for an urban farming decision support system that coordinates the activities of many independent producers to target collective goals.

In this paper, we describe application of Neuroevolution to a P2P lending problem in which a credit evaluation model is updated based on streaming data. We apply the algorithm Neuroevolution of Augmenting Topologies (NEAT) which has not been widely applied generally in the credit evaluation domain. In addition to comparing the methodology with other widely applied machine learning techniques, we develop and evaluate several enhancements to the algorithm which make it suitable for the particular aspects of online learning that are relevant in the problem. These include handling unbalanced streaming data, high computation costs, and maintaining model similarity over time, that is training the stochastic learning algorithm with new data but minimizing model change except where there is a clear benefit for model performance

Agricultural innovation is imperative in order to meet global challenges to sustainably feed large urban populations. This paper contributes a modelling framework for urban agriculture, and an implementation in a scenario based on the fast growing mega city of Shenzhen located near Hong Kong in southern China. We also review related work and provide a gap analysis between requirements for modelling modern urban agricultural systems versus related work that looks at agricultural supply chains, production, and land use. The proposed framework will facilitate developing a novel decision support system to coordinate decentralized urban agricultural production units in order to realize, at scale, numerous benefits from co-locating production and consumption in the urban environment.

Domain names can be traded via online market places and auctions. Speculation can be lucrative, with high value transactions reaching into tens of millions of dollars. This paper proposes a framework for automated domain name appraisal and evaluates several formulations of the problem with real world data. A dynamic nonlinear valuation modelling process is defined using machine learning techniques. Attributes or value factors are derived from short domain name text strings as well as a variety of other contextual data able to be obtained online from open sources. A data set of 9.975 million domains is used for evaluation and results show that search engine query data is a primary driver of value but using extracted text features can facilitate higher performance in distinguishing high value domains particularly when used with ensemble learning.

As digital infrastructure expands in new regions of the globe, developing ways to include more diverse information in financial decisions is important. However, making use of novel data sources requires developing methods to evaluate credit with diverse and complex datasets with missing information, dynamic patterns and relationships with decision recommendations, and larger feature sets. Feature selection is one approach that can support the application of machine learning to dynamically build models for credit evaluation with complex data. Genetic algorithms (GAs) have been proved to reach good performance in other research, with high computation cost though. In this paper, we review existing GA approaches and test and develop a novel method based on niching and the use of subpopulations with different data for fitness evaluation. This formulation allows less computation cost, even with better prediction performance in feature selection. In further experiments, we compare the proposed GA-based feature selection approaches in four traditional credit datasets and a novel emerging market dataset from China. The results indicate that the advanced GA-based feature selection methods perform more effectively.

As countries develop digital financial infrastructure, a wide range of economic activities expand and grow in importance: from personal loans, to the rapidly developing networked microfinance industry, to mobile telephone services and real estate transactions and so on. Personal credit is also a foundation of trust for facilitation of integrated societal transactions more generally. In emerging markets there is, however, a gap between the requirement for establishing a credit or trust rating and the lack of a credit record. The development of methodologies for greater financial integration of growing economies has the potential to have a significant impact on increasing the GDP of developing economies (4-12% according to a recent McKinsey Global Institute report). In this paper, we develop and test a methodology for feature selection and test its in standard datasets from large institutions in mature market economies, and a recent dataset which illustrates characteristics of emerging markets. The results show performance in classification can be maintained while runtime can be reduced when using a GA for feature selection in a range of machine learning techniques.

The world is currently facing significant challenges in feeding a growing population with declining resources. Urban agriculture and vertical farming have the potential to provide a revolutionary new food supply and distribution network capable of feeding large populations in the 21st Century; as well as increase quality and reduce negative impacts on the natural environment. The concept has attracted a lot of attention from governments and business throughout the world recently. This paper describes a framework for applying technologies from Agent Based Models, Simulation and Computational Intelligence to analyze, optimize and manage “ecosystems” for urban agriculture and vertical farming for food production from the perspective of stakeholders including consumers, producers, and policy makers.