Reliable forecasting based on observational evidence is useful in individual and firm decision-making, as well as governmental planning, regulation, and many other activities that rely on future economic projections. For example, central banks need information about a future path of inflation in order to adjust its interest rate. Companies forecast future sales in order to adjust their production. This project sets out to develop three new machine learning (ML) methods that address structural instabilities and nonstationarities that are well known to be present in economic and financial systems and that complicate variable selection and tuning parameter choices. By virtue of their attention to these characteristics, the new methods are expected to outperform traditional econometric methods and existing ML methods and produce more accurate economic and financial forecasting, which in turns leads to better decisions.
In this Human-Computer Interaction research, the research team will design a novel system that addresses the low wage of online crowd work—also known as online gig-economy. By using knowledge from mechanism design in the economics literature, the research team will design and develop user interfaces through machine learning models that:
- Present information to encourage crowdsourcing requesters pay a fairer wage to online workers; and
- Use nudging messages and information visualization to persuade workers to submit high-quality work.
This research collaboration with IBM aims to develop the optimisation capabilities to build a cutting-edge resilient supply chain, leveraging data science to preserve the continuity and consistency of product supply and meet business obligations for product delivery and service to customers in the face of both short-term operational and longer-term strategic disruptions. In this project, the team seeks to leverage IBM’s relevant internal, supplier-provided, public and subscription data sources to improve operational decision-making capability to proactively anticipate and respond to disruptive events, and to enable resiliency evaluations for products, product families, or tiered supply networks.
With its open and broadcasting nature, social media is often the platform to go to when an incident occur. This study concentrates on urban events, which can be an incident of social disorder or a crisis such as a sudden riot in a city. While prior studies mainly focus on detecting crisis events, this new study goes beyond detection to focus on actionable intelligence and proposes an in-depth analysis of the event including timeline-based situational and emotional changes. The objectives of this study are, 1) develop an approach to extract and analyze actionable situational intelligence from social media, and 2) research on new/novel approaches to summarize key information for interpretation of the results, e.g., relationship of key entities.
The "SmartBFA 2.0" project aims to build a "Google Maps" equivalent for wheelchair users, so that they can find barrier-free access paths when navigating around Singapore. This objective is in line with Singapore's vision towards building a smart and inclusive city for everyone.
A major innovation of the research team's project is the incorporation of crowdsourced sensor inputs; in particular, they aim to solicit multi-modal data collected from a smartphone app to supplement the accessibility information that they have collected using specially-designed sensors. They also seek to collect user feedback, so as to make their system more useful to wheelchair users.
"Learning by doing” (LBD) is the phenomenon where a worker’s productivity rises with cumulative production experience. As LBD requires no additional investment in hiring or equipment investment, it is viewed by many as an important channel for firms to achieve productivity growth. Unfortunately, although conceptually simple and intuitive, the sources and enablers of LBD remain a mystery; as a result, even when a firm intends to facilitate LBD among its employees, it is not clear how to effectively achieve it. This challenge originates from the difficulty in quantifying and isolating the effects of LBD, and even in a few instances where the measurement of LBD effects (in terms of productivity) is made possible by natural events, these measurements are typically only at the aggregate level. In this project, the team aims to build a novel Big Data framework to measure the LBD effects for workers in the transport gig economy in Singapore. Their ambition is to measure LBD effects at not just the productivity level, which is easily tainted by other factors, but also at the skill level. They plan to achieve this by mining drivers’ microscopic movement traces and trip fulfilment (including both taxi and ride-hailing drivers), and quantify drivers’ skills in anticipating demands and competition from other drivers. Their research will provide a rare view into how big data can revamp the understanding of labor productivity and LBD effects at the individual level, and it will help policy makers and platform operators to come up with policies that are more effective in helping workers cope with competitions and sudden changes such as disruptions brought about by the COVID-19 pandemic.
In this multi-pronged initiative, we propose to build a framework for developing certifiable AI systems systematically, i.e. with the help of theories, tools, certification standards and processes. This is motivated by the many recently discovered problems on existing AI techniques and systems, e.g. adversarial samples, privacy and fairness issues, as well as the many ad hoc attempts on fixing them. For AI techniques to truly become part of a wide digital transformation across many industries, it is vital that we have foundational mechanisms to quantify the problems in AI models, and rectify the discovered problems.
This five-year longitudinal study with the Ministry of Sustainability and the Environment (MSE) aims to quantify and qualify the economic and environmental impact of the Extended Producer Responsibility (EPR) framework for e-waste in Singapore. The findings will aid MSE in assessing the effectiveness of the e-waste EPR and refining it for future phases.
This project aims at developing a software engine that enables planners to generate optimised routing plans based on a given set of data inputs subject to constraints. This work is an offshoot from the Collaborative Urban Delivery Optimisation (CUDO) project which was completed under the Fujitsu-SMU Urban Computing and Engineering (UNiCEN) Corp Lab, that was funded by the National Research Foundation (NRF). The project will customise and extend the functionalities of the CUDO engine developed at SMU, and integrate the engine into Y3 Technologies’ enterprise platform system via an Application Programming Interface (API).
Deep learning has enabled significant advances in applications involving image, text and audio data, in applications such as surveillance, machine translation and speech recognition. These successes have positioned deep learning as a promising approach to address critical challenges (reducing defects, design-time and down-time) in the advanced manufacturing and engineering (AME) domain. A major barrier to this broader application of deep learning is its need for large, labeled datasets to obtain good performance. Thus, the team aims to develop novel deep learning methods that can learn with 10 to 100 times less data as compared to current approaches. This project will enable deep learning to be used in a wider range of applications especially where data is scarce or expensive to obtain. The team will also demonstrate their methods using real-world data from the three identified AME applications (tentatively defect identification, predictive maintenance and circuit design) to show progress and applicability to the AME domain. This project is a collaboration between A*STAR’s I2R, SMU, SUTD, NTU and NUS.