One third of the reason why mega-projects fail are due to “out of hand” uncertainty. The proposed framework for Artificial Intelligence (AI) as a monitoring system can help executives manage and reduce uncertainties impacting the project from external domains, such as economics, finance, or geopolitics. Accounting for different risk perspectives and incorporating accurate and reliable forecasts at early stages can help risk-management practices by information decisions based on foresight intelligence.

This study benchmarks model reliability to assess the status of various mega-project status. The results show that ex-ante predictions for large development projects can help reduce project overrun costs, reputation risks, and provide an early warning before conventional evaluations of project outcome. The documented methods can help identify project failures earlier in the project lifecycle and inform institutional risk management strategies.

The polarization of income in US cities presents significant risks to the resilience of local communities. Existing measurement science for economic disparity (e.g. Gini coefficient) do not explicitly consider a probability distribution with information, deficiencies and uncertainties associated with the underlying income distribution. This paper introduces probabilistic principles of Shannon Entropy to quantity uncertainty and risk in economic disparity with theoretic and empirical evidence using inter-and-intra city level data during the economic recovery (2009-14). The evidence shows polarization of household incomes within and across Baltimore, Washington, DC and San Francisco. Medium income tracts tend to reveal high entropy corresponding to greater equality and parity with higher uncertainty.

Using a newly constructed dataset on trade in services for 192 countries from 1970 to 2014, this paper shows that services currently constitute one-fourth of world trade and an increasingly important component of global production. A detailed analysis of patterns and stylized facts reveals that exports of services are not only gaining strong momentum and catching up with exports of goods in many countries, but they could also trigger a new wave of trade globalization. Research applications of the trade in service dataset on structural transformation, resilience, labor reallocation, and income distribution are outlined.

This paper provides a benchmarking of ensemble deep learning techniques for reliable and accurate time-series forecasting for financial, economic, and geopolitical information at various time frequencies, including monthly, quarterly, and annual.

This study presents a novel deep learning framework where Dynamic Time Warping (DTW), Hierarchical Clustering Analysis (HCA), and long-short term memory (LSTM) are used to predict annual state level per capita Net GDP (NSDP) growth using data from the Reserve Bank of India (RBI) and Niti Ayog.

This study presents a novel deep learning framework where

Dynamic Time Warping (DTW), Hierarchical Clustering Analysis

(HCA), and long-short term memory (LSTM) are used to predict

daily protests movements in USA based on event popularity from

the Global Database of Events, Location, and Tone (GDELT)

database.The developed model can be used to inform decision makers on uncertain-adjusted prediction for protests in a given country on a daily basis.

The rise in economic disparity presents significant risks to global social order and the resilience of local communities. However, existing measurement science for economic disparity (e.g. Gini coefficient) do not explicitly consider a probability distribution with information, deficiencies and uncertainties associated with the underlying income distribution. This paper introduces probabilistic principles of Shannon Entropy to quantity uncertainty and risk in economic disparity with theoretic and empirical evidence using global, national and city level data. Entropy and information-based conflict rise as world incomes convergence. High entropy instances can resemble both happy and prosperous societies as well as socialist-communist social structure. Low entropy signals high-risk tipping points for anomaly and conflict detection with higher confidence.

This study presents a novel deep learning framework where Dynamic Time Warping (DTW), Hierarchical Clustering Analysis (HCA), and long-short term memory (LSTM) are combined for daily stock price forecasting. The developed model can be used to inform decision makers on uncertain-adjusted trading strategies for next day’s closing prices. The proposed model outperforms other similar models in both predictive accuracy and profitability performance with a scalable and modular framework.

Full Dissertation Available Upon Request

Economic Complexity is a set of network-based and algorithmic methods for the study of economic development and competitiveness. In this framework, Economic Fitness is an innovative approach that improves the mathematical and conceptual scheme. For convenience, these methods were originally conceived on trade in goods. This paper extends the Economic Fitness methodology to include a trade in services element to yield a universal matrix of world trade and thus provide a more complete picture of a country’s development and global competitiveness. The results show that (i) the competitiveness of many countries was previously over- or underestimated, that is, many countries gain or lose positions in the ranking of economic fitness when services trade is considered alongside goods; and (ii) complex services tend to cluster with complex manufacturing, suggesting a common capabilities structure. These findings show how developing complex services aids diversification strategies for developing countries.

A non-linear iterative algorithm is applied that ranks the
‘fitness’ of countries based on their diversity and ‘complexity’ of their specialization. The results show that niche technology-enabled service exports are some of the most complex components in the world trade network. Moreover, middle-income countries and resource rich countries show greater economic fitness (competitiveness) when service exports are integrated in the world trade network. Finally, the paper provides a framework to inform economic policy decisions concerning export diversification strategies in developing countries.

Like many resource-rich countries, oil exporting Angola is having difficulty in graduating to a high-income status without diversifying its sources of income in products and services that have more stable prices. It also faces the additional challenge of rejuvenating its war-destructed economic base. We apply a variety of technical metrics to evaluate export concentration in Angola. Regardless of the measure used to gauge concentration, it is apparent that in the medium term, its skill levels are the key challenge to Angola’s diversification in higher value products and services. In the immediate term, rebuilding some of the industries in which Angola had a natural comparative advantage in the 1960s and ‘70s seems a prudent first step towards diversification....

We study the impact of fluctuations in global oil prices on domestic inflation using an unbalanced panel of 72 advanced and developing economies over the period from 1970 to 2015. We find that a 10 percent increase in global oil inflation increases, on average, domestic inflation by about 0.4 percentage point on impact, with the effect vanishing after two years and being similar between advanced and developing economies. We also find that the effect is asymmetric, with positive oil price shocks having a larger effect than negative ones. The impact of oil price shocks, however, has declined over time due in large part to a better conduct of monetary policy. We further examine the transmission channels of oil price shocks on domestic inflation during the recent decades, by making use of a monthly dataset from 2000 to 2015. The results suggest that the share of transport in the CPI basket and energy subsidies are the most robust factors in explaining cross-country variations in the effects of oil price shocks during the this period.

We find that Okun’s Law holds quite well for most U.S. states but the Okun coefficient—the responsiveness of unemployment to output—varies substantially across states. We are able to explain a significant part of this cross-state heterogeneity on the basis of the state’s industrial structure. Our results have implications for the design of state and federal policies and may also be able to explain why Okun’s Law at the national level has remained quite stable over time despite an enormous shift in the structure of the U.S. economy from manufacturing to services.

How to model time to the next recession and early warning risks that accelerate the arrival of an economic recession? This paper provides a novel approach based on reliability theory to model the economic resilience function and the mean time to recession. A recession year is treated as an economic failure providing the inter-arrival time between recessions. In this approach, time is the main agent of failure. We show robustness of our estimates using annual, quarterly, and monthly statistics for the US economy from 1960-2016. We then use the proportional hazard model to incorporate shocks in short-term structure of treasury yields. We, additionally, propose an Alternating Generalized Renewal process that accommodates the dynamics of business cycle fluctuations and downtime for recession and recovery. Our results document prediction capabilities for the Great Recession and provide forecasts for the expected time to arrival for future recessions.

Harmonic Drives are used ubiquitously in aerospace and robotics due to its high torque capacity, size and reduction ratio. However, their use in high radiation environments is still prone to failure. The literature on component and system reliability of space equipment is silent on the radiation induced failure of such gearboxes. This paper documents a new channel of radiation induced failure of harmonic drives which is relatively unexplored method of failure. We use the Master Curve Approach to calibrate the shift in upper shelf energy of the various material elements used in production of harmonic drive gearboxes. Estimations are made on the changes in fracture toughness based on various radiation environments. Radiation hardening could make

the gearboxes more resilient to neutron embrittlement of the SUS 304L Stainless Steel in flexspline. Our model shows that the gearbox system could wear out before its mission life in fast neutron radiation, where particle energies are in excess of 1 MeV. This type of radiation is fairly rare in large fluxes; while it does have a high enough flux in space to cause issues for humans, it is not high enough to appreciably impact steels. One of the few environments of interest for this effect is inside of nuclear reactors. Our study finds that without accounting for

neutron embrittlement, the predicted fatigue life of a harmonic drive can be off by nearly two orders of magnitude. From this model it was observed that when irradiated, the component strength of the harmonic drive will increase, while its fatigue life will decrease.