ISM Joint Seminar

Thousands of music tracks are uploaded to the Internet every day through websites and social networks that focus on music. While some content has been popular for decades, some tracks that have just been released have been ignored. What makes a music track popular? Can the duration of a music track’s popularity be explained and predicted? By analysing data on the performance of a music track on the ranking charts, coupled with the creation of machine-generated music semantics constructs and a variety of other track, artist and market descriptors, this research tests a model to assess how track popularity and duration on the charts are determined. For those music tracks that have high duration, a prediction model for the temporal diffusion on social networks was proposed, by considering user relationships, music semantics, and impacts from the external environment.

This research examines the potential for time-series econometrics techniques, coupled with explanatory data analytics methods to identify and interpret intertemporal and geospatial shocks that occur in global payments-related financial telecom. A key research question in this inquiry is: What constitutes an anomaly in the observable patterns of payments that can be diagnosed, described and assessed to create the basis for understanding the changing information content of payment message flows. This research employs a data set on financial messaging that involves more than 200 countries, a period of 12 years, and greater than 1 million observations. Our results suggest a number of different ways that global payment-related messages, similar to credit card transaction flow in national-level regional and local economies, can be useful signals of a range of economic change and growth issues research directions that can bring together issues. This research also involves a politics, law and economics perspective for international banking that will help to transform future research in the technology-related policy analytics domain.

This study evaluates transition pathways in electricity generation and their impacts on future water use using an electricity generation capacity expansion model. Scenarios that are compliant or not compliant the U.S. Environmental Protection Agency's proposed carbon pollution standards – the New Source Performance Standards and Clean Power Plan – are considered. Using the Electric Reliability Council of Texas Region as an illustration, the scenarios with the carbon regulations are shown to have lower water use from the power sector than the continuation of the status quo, with more electricity generation from coal than natural gas. This is due to an increase in electricity generation from renewable sources and natural gas combined cycle (NGCC) plants that is influenced by the CO2 allowance price. The scenario that considers retrofitting carbon capture and storage (CCS) to existing coal and NGCC plants has lower electricity cost and higher water use compared with the scenario that does not consider a CCS retrofit. Water withdrawal will be much higher if the CO2 price for enhancing oil recovery is higher than $10 per short ton because of more electricity generation from existing coal with CCS retrofit. Water withdrawal limits affect electricity generation, decreasing it from power plants with once-through cooling, but this will slightly increase water consumption.

Photovoltaic (PV) systems are a small-scale technology for renewable electricity generation, which can be deployed on the rooftops of buildings. This technology enables individual homeowners to participate in the shaping of a sustainable energy system based on renewable energies. A considerable amount of research has focused on the drivers of the adoption of roof-mounted PV systems, such as the incoming irradiance on rooftops or household income. Putting the findings to use, e.g. via recommender systems to promote the PV technology, remains a challenge. We propose a method for predicting the likelihood of homeowners to adopt PV systems using 3D-building data and existing PV installations in the area of interest. This approach can be used as a recommender system for municipalities to inform homeowners about the suitability of their buildings for PV systems. However, our method is also relevant for marketing in other domains where building characteristics are related to individual decision-making, such as political campaigning or newspaper sales.