Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeep Sequence Modeling: Development and Applications in Asset Pricing
91
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We predict asset returns and measure risk premia using a prominent technique from artificial intelligence -- deep sequence modeling. Because asset returns often exhibit sequential dependence that may not be effectively captured by conventional time series models, sequence modeling offers a promising path with its data-driven approach and superior performance. In this paper, we first overview the development of deep sequence models, introduce their applications in asset pricing, and discuss their advantages and limitations. We then perform a comparative analysis of these methods using data on U.S. equities. We demonstrate how sequence modeling benefits investors in general through incorporating complex historical path dependence, and that Long- and Short-term Memory (LSTM) based models tend to have the best out-of-sample performance.
rate research
Read More
This paper investigates whether security markets price the effect of social distancing on firms operations. We document that firms that are more resilient to social distancing significantly outperformed those with lower resilience during the COVID-19 outbreak, even after controlling for the standard risk factors. Similar cross-sectional return differentials already emerged before the COVID-19 crisis: the 2014-19 cumulative return differential between more and less resilient firms is of similar size as during the outbreak, suggesting growing awareness of pandemic risk well in advance of its materialization. Finally, we use stock option prices to infer the markets return expectations after the onset of the pandemic: even at a two-year horizon, stocks of more pandemic-resilient firms are expected to yield significantly lower returns than less resilient ones, reflecting their lower exposure to disaster risk. Hence, going forward, markets appear to price exposure to a new risk factor, namely, pandemic risk.
AI and reinforcement learning (RL) have improved many areas, but are not yet widely adopted in economic policy design, mechanism design, or economics at large. At the same time, current economic methodology is limited by a lack of counterfactual data, simplistic behavioral models, and limited opportunities to experiment with policies and evaluate behavioral responses. Here we show that machine-learning-based economic simulation is a powerful policy and mechanism design framework to overcome these limitations. The AI Economist is a two-level, deep RL framework that trains both agents and a social planner who co-adapt, providing a tractable solution to the highly unstable and novel two-level RL challenge. From a simple specification of an economy, we learn rational agent behaviors that adapt to learned planner policies and vice versa. We demonstrate the efficacy of the AI Economist on the problem of optimal taxation. In simple one-step economies, the AI Economist recovers the optimal tax policy of economic theory. In complex, dynamic economies, the AI Economist substantially improves both utilitarian social welfare and the trade-off between equality and productivity over baselines. It does so despite emergent tax-gaming strategies, while accounting for agent interactions and behavioral change more accurately than economic theory. These results demonstrate for the first time that two-level, deep RL can be used for understanding and as a complement to theory for economic design, unlocking a new computational learning-based approach to understanding economic policy.
Family history is usually seen as a significant factor insurance companies look at when applying for a life insurance policy. Where it is used, family history of cardiovascular diseases, death by cancer, or family history of high blood pressure and diabetes could result in higher premiums or no coverage at all. In this article, we use massive (historical) data to study dependencies between life length within families. If joint life contracts (between a husband and a wife) have been long studied in actuarial literature, little is known about child and parents dependencies. We illustrate those dependencies using 19th century family trees in France, and quantify implications in annuities computations. For parents and children, we observe a modest but significant positive association between life lengths. It yields different estimates for remaining life expectancy, present values of annuities, or whole life insurance guarantee, given information about the parents (such as the number of parents alive). A similar but weaker pattern is observed when using information on grandparents.
A new framework for asset price dynamics is introduced in which the concept of noisy information about future cash flows is used to derive the price processes. In this framework an asset is defined by its cash-flow structure. Each cash flow is modelled by a random variable that can be expressed as a function of a collection of independent random variables called market factors. With each such X-factor we associate a market information process, the values of which are accessible to market agents. Each information process is a sum of two terms; one contains true information about the value of the market factor; the other represents noise. The noise term is modelled by an independent Brownian bridge. The market filtration is assumed to be that generated by the aggregate of the independent information processes. The price of an asset is given by the expectation of the discounted cash flows in the risk-neutral measure, conditional on the information provided by the market filtration. When the cash flows are the dividend payments associated with equities, an explicit model is obtained for the share-price, and the prices of options on dividend-paying assets are derived. Remarkably, the resulting formula for the price of a European call option is of the Black-Scholes-Merton type. The information-based framework also generates a natural explanation for the origin of stochastic volatility.
We propose three different data-driven approaches for pricing European-style call options using supervised machine-learning algorithms. These approaches yield models that give a range of fair prices instead of a single price point. The performance of the models are tested on two stock market indices: NIFTY$50$ and BANKNIFTY from the Indian equity market. Although neither historical nor implied volatility is used as an input, the results show that the trained models have been able to capture the option pricing mechanism better than or similar to the Black-Scholes formula for all the experiments. Our choice of scale free I/O allows us to train models using combined data of multiple different assets from a financial market. This not only allows the models to achieve far better generalization and predictive capability, but also solves the problem of paucity of data, the primary limitation of using machine learning techniques. We also illustrate the performance of the trained models in the period leading up to the 2020 Stock Market Crash (Jan 2019 to April 2020).
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
