Page 13 - Data Science Algorithms in a Week

x Luis Rabelo, Sayli Bhide and Edgar Gutierrez

ability to be applied in variety of healthcare systems. The methodology developed is the
first of this kind.
• Simulation Modeling: can be used as an important methodology to capture and
develop knowledge and complement the implementation of intelligent system. The
chapter “The Utilization of Case-Based Reasoning: A Case Study of the Healthcare
Sector Using Simulation Modeling” applies a combination of discrete event simulations
(DES) and case based reasoning (CBR) to assist in solving new cases in healthcare
systems. An important objective of this approach is that it can improve the stakeholders’
involvement by eliminating the need for simulation or statistical knowledge or
experience. A case study on EDs which face multiple resource constraints including
financial, labor, and facilities is explained by Khaled Alshareef, Ahmad Rahal, and
Mohammed Basingab. The applications of DES-CBR provided solutions that were
realistic, robust, and more importantly the results were scrutinized, and validated by field
experts.
• Agent Based Modeling and Simulation and its Application to E-commerce: by
Oloruntomi Joledo, Edgar Gutierrez, and Hathim Bukhari presents an application for a
peer-to-peer lending environment. The authors seek to find how systems performance is
affected by the actions of stakeholders in an ecommerce system. Dynamic system
complexity and risk are considered in this research. When systems dynamics and neural
networks are combined along with at the strategy level and agent- based models of
consumer behavior allows for a business model representation that leads to reliable
decision-making. The presented framework shares insights into the consumer-to-
consumer behavior in ecommerce systems.
• Artificial Intelligence for the Modeling and Prediction of the Bioactivities of
Complex Natural Products: by Jose Prieto presents neural networks as a tool to predict
bioactivities for very complex chemical entities such as natural products, and suggests
strategies on the selection of inputs and conditions for the in silico experiments. Jose
Prieto explains that neural networks can become reliable, fast and economical tools for
the prediction of anti-inflammatory, antioxidant, antimicrobial and anti-inflammatory
activities, thus improving their use in medicine and nutrition.
• Predictive Analytics: is one of the most advanced forms of analytics and AI
paradigms that are the core of these predictive systems. The chapter “Predictive Analytics
for Thermal Coal Prices using Neural Networks and Regression Trees” by Mayra
Bornacelli and Edgar Gutierrez aims to deliver price predictive analytics models. A
necessity for many industries. This chapter is targeted towards predicting prices of
thermal coal. By implementing the Delphi methodology along with neural networks,
conclusions can be reached about global market tendencies and variables. Although
neural networks outperformed regression trees, the latter created models which can be
easily visualized and understood. Overall, the research found that even though the market
of thermal coal is dynamic and the history of its prices is not a good predictive for future