Research

Publications

"Profit allocation in investment-based crowdfunding with investors of dynamic entry times." with Lindong Liu and Gongbing Bi .

  • Yang, Y., Bi, G. and Liu, L., 2020. Profit allocation in investment-based crowdfunding with investors of dynamic entry times. European Journal of Operational Research, 280(1), pp.323-337.

  • Abstract: Even distribution is a normal profit allocation mechanism for investment-based crowdfunding projects on many platforms. In other words, the investors with the same pledging funds will be paid evenly when the investment ends. The even allocation mechanism works well under the assumption that the investors arrive at the platform simultaneously. However, in practice, the investors are sequential, therefore, the stories are different when considering the dynamic entry times of the investors. In this paper, we study ways to design appropriate profit allocation mechanisms to enhance the success rate of an investment-based crowdfunding project. The basic model focuses on the two-investor case, where only two investors with dynamic entry times are considered. The profit allocation mechanism is shown to have great impacts on the pledging probabilities of investors, as well as the success rate of a project. After that, we shift our focus to the two-cohort case, where dynamic investors are assumed to arrive at the platform as two sequential cohorts. By taking the sizes of each cohort into consideration, we are able to analyze the success rate of a project under various practical situations. Finally, we implement some numerical experiments to generalize our studies to the situations where (i) there are more than two pledging periods for the investors, (ii) the herding effect of the investors is considered, and (iii) the valuations of the investors are assumed to be normally distributed. Our main results still hold under these general situations.

"Distributionally worst-case moments under partial ambiguity." with Qihe Tang.

  • Tang, Q. and Yang, Y., 2022. Distributionally worst-case moments under Partial Ambiguity. Under revision.

  • Abstract: The model uncertainty issue is pervasive in virtually all applied fields but especially critical in insurance and finance. To hedge against the uncertainty of the underlying probability distribution, which we refer to as ambiguity, distributionally robust optimization (DRO) has been well developed during recent years. However, this approach often yields results that are overly conservative. We argue that in most practical situations a generic risk is realized from multiple scenarios. In some ordinary scenarios, the risk may be subject to negligible ambiguity so that it is safe to trust the reference distributions, and hence we can apply DRO only to the other scenarios where ambiguity is significant. We implement this idea into the robust estimation of the moments of a risk in the hope to alleviate the over-conservativeness issue. Note that under this consideration ambiguity exists in both the scenario indicator and the risk realization in the corresponding scenario, leading to a twofold ambiguity issue. We employ the Wasserstein distance to construct an ambiguity ball and then carefully disentangle the ambiguity along the two folds so as to link our robust estimation problem to established DRO results. Our main result is a closed-form robust estimate for the moments. Our numerical studies illustrate that the consideration of partial ambiguity indeed greatly alleviates the over-conservativeness issue.

  • Presented at: 24th International Congress on Insurance: Mathematics and Economics (IME); 11th Conference in Actuarial Science & Finance (CASF); UNSW 3MT Competition and Industry Workshop

"High-quality credit portfolios under the interplay of common shock and systematic risk" with Qihe Tang and Yang Yang.

  • Tang, Q., Yang, Y. and Yang, Y., 2022. High-quality credit portfolios under the interplay of common shock and systematic risk. Under review.

  • Abstract: Consider a large investment portfolio that is crucially important for social and economic security and hence requires a prudent examination of the portfolio loss due to defaults. Suppose that the assets in the portfolio are exposed to multilevel risks including idiosyncratic risk, systematic risk, and common shock. We argue that common shock and systematic risk may interplay with each other, form a causal loop, and exhibit a joint extreme scenario. To quantify the portfolio loss, a one-period structural model is employed in which latent variables governing individual defaults follow a mixture structure integrating the multilevel risks. An asymptotic study of the portfolio loss due to defaults is conducted under a joint regular variation structure of the common shock factor and the systematic risk factor. Our main finding is that the tail dependence between the two risk factors, besides their marginal tails, is another driving force in the portfolio loss. We show, both analytically and numerically, that this tail dependence, if underestimated or even ignored, may lead to disastrous consequences to portfolio risk management.

  • Presented at: 25th International Congress on Insurance: Mathematics and Economics (IME); 2022 Australasian Actuarial Education & Research Symposium

Developing Projects