A Big Data Approach to Cargo Type Prediction and Its Implications for Oil Trade Estimation (With Xiwen Bai, Qi Wang, and Zhongjun Ma, 2022) - Transportation Research Part E: Logistics and Transportation Review, 165(9), 102831.
Abstract: To estimate global crude oil trade flows, current research either considers only crude oil tankers, or simply applies external information to distinguish between crude and refined product oil cargoes transported by coated product tankers; these limitations often reduce an estimation’s accuracy or compromise replicability. Our methodology directly addresses these issues by applying the random forest (RF) ensemble learning technique to Automatic Identification System (AIS) data in order to predict the cargo types of coated product tankers. By leveraging domain knowledge, we construct a set of unique input variables for the RF model, and use its predictions to quantify the global crude oil trade in a more accurate manner. Our estimation shows that coated product tankers were responsible for approximately 8% of global seaborne crude oil trade from 2017–2020. Further, unanticipated variations in the crude oil volume carried by these tankers are consistent with several major historical oil trade disruptions. Our study further extends current applications of AIS data in the domains of operations management and maritime transportation, and facilitates the exploration of the more minute characteristics of oil transportation. The resulting shipping dataset and associated decomposition strategy also enable relevant stakeholders to quickly identify emerging trade flow risks and adapt more effectively.
Presentations: 10th International Conference on Logistics and Maritime Systems (2021, also known as LOGMS 2021).
My presentation of the paper at LOGMS 2021 can be accessed here.
Abstract: this paper uses a unique dataset, encompassing the entire product tanker fleet from 2017-2020, to study congestion in oil transportation markets. From this we establish three novel facts: (1) congestion significantly reduces tankers' contracting probability; (2) tankers switch frequently between markets; and, (3) oil trade shocks propagate in the economy through a transportation network. We develop a novel search and matching model by incorporating these facts with the interactions between oil exporters, tankers, and a final good producer. We show that shipping market congestion attenuates over one third of the volatility in oil trade and final good production, while increasing price fluctuations by more than tenfold. We also show that the endogenous adjustment of the oil transportation network and the resulting congestion effect are almost irrelevant for aggregate fluctuations; it is the exogenous oil trade shocks that generate large fluctuations.
Presentations: Commodity & Energy Markets Association Annual Meeting (2022), Jinan University (2022), Xi'an Jiaotong - Liverpool University (2021), Cardiff Business School (2021), International Association of Maritime Economists Conference (2021, also known as IAME 2021), The Hong Kong Polytechnic University (2021), Australasia Meeting of the Econometric Society (2021), China Meeting of the Econometric Society (2021), 8th Annual MMF PhD Conference (2021), Tsinghua University (2021), Shandong University (2021), Oxford Macro Working Group Seminar (2021).
The paper has been awarded the 2021 Peter Sinclair Prize at the 8th Annual MMF PhD Conference .
The paper has been awarded the 2022 PhD Prize Award at the CEMA 2022 Conference.
An earlier version of the paper circulated under the title "The 'Missing' Link: How Does Oil Transportation Trigger Macroeconomic Implications''.
The Agricultural Exodus in the Philippines: Are Wage Differentials Driving the Process? (With Eugenio Cerutti) - Under Review
Abstract: lagging labor reallocations outside agriculture amid sustained low agricultural productivity have been a key feature in the Philippines over the past 15 years. An analysis of the labor adjustments in and out of agriculture shows that a variety of factors have influenced this process. We find that the widening of wage differentials with non-agricultural sectors, improvements in labor market efficiency, and better transport infrastructure are largely associated with growing outflows of labor from agriculture, whilst the lack of post-primary education and the presence of agricultural clusters hinder such outflows. In contrast to the traditional view that agricultural employment outflows are largely driven by productivity differences and wage differentials, our results emphasize the roles of education as well as transport infrastructure in facilitating labor reallocations from agriculture to non-agriculture.
Presentations: Philippine Institute for Development Studies (PIDS) Research Workshop (2021), IMF APD Seminar (2020).
The paper was previously circulated as an IMF Working Paper (No. 2021/220).
Appendix I. Impact Of COVID-19 On The Philippines' Labor Market
Chapter 1. Economic Update
Chapter 3. The Future We Want: Is It Affordable?