ترغب بنشر مسار تعليمي؟ اضغط هنا

Deep learning Profit & Loss

58   0   0.0 ( 0 )
 نشر من قبل Giacomo Bormetti
 تاريخ النشر 2020
  مجال البحث مالية
والبحث باللغة English




اسأل ChatGPT حول البحث

Building the future profit and loss (P&L) distribution of a portfolio holding, among other assets, highly non-linear and path-dependent derivatives is a challenging task. We provide a simple machinery where more and more assets could be accounted for in a simple and semi-automatic fashion. We resort to a variation of the Least Square Monte Carlo algorithm where interpolation of the continuation value of the portfolio is done with a feed forward neural network. This approach has several appealing features not all of them will be fully discussed in the paper. Neural networks are extremely flexible regressors. We do not need to worry about the fact that for multi assets payoff, the exercise surface could be non connected. Neither we have to search for smart regressors. The idea is to use, regardless of the complexity of the payoff, only the underlying processes. Neural networks with many outputs can interpolate every single assets in the portfolio generated by a single Monte Carlo simulation. This is an essential feature to account for the P&L distribution of the whole portfolio when the dependence structure between the different assets is very strong like the case where one has contingent claims written on the same underlying.



قيم البحث

اقرأ أيضاً

We present a general framework for portfolio risk management in discrete time, based on a replicating martingale. This martingale is learned from a finite sample in a supervised setting. The model learns the features necessary for an effective low-di mensional representation, overcoming the curse of dimensionality common to function approximation in high-dimensional spaces. We show results based on polynomial and neural network bases. Both offer superior results to naive Monte Carlo methods and other existing methods like least-squares Monte Carlo and replicating portfolios.
One of the key elements in the banking industry rely on the appropriate selection of customers. In order to manage credit risk, banks dedicate special efforts in order to classify customers according to their risk. The usual decision making process c onsists in gathering personal and financial information about the borrower. Processing this information can be time consuming, and presents some difficulties due to the heterogeneous structure of data. We offer in this paper an alternative method that is able to classify customers profiles from numerical and nominal attributes. The key feature of our method, called LVQ+PSO, is the finding of a reduced set of classifying rules. This is possible, due to the combination of a competitive neural network with an optimization technique. These rules constitute a predictive model for credit risk approval. The reduced quantity of rules makes this method not only useful for credit officers aiming to make quick decisions about granting a credit, but also could act as borrowers self selection. Our method was applied to an actual database of a credit consumer financial institution in Ecuador. We obtain very satisfactory results. Future research lines are exposed.
Online trading has attracted millions of people around the world. In March 2021, it was reported there were 18 million accounts from just one broker. Historically, manipulation in financial markets is considered to be fraudulently influencing share, currency pairs or any other indices prices. This article introduces the idea that online trading platform technical issues can be considered as brokers manipulation to control traders profit and loss. More importantly it shows these technical issues are the contributing factors of the 82% risk of retail traders losing money. We identify trading platform technical issues of one of the worlds leading online trading providers and calculate retail traders losses caused by these issues. To do this, we independently record each trade details using the REST API response provided by the broker. We show traders log activity files is the only way to assess any suspected profit or loss manipulation by the broker. Therefore, it is essential for any retail trader to have access to their log files. We compare our findings with brokers Trustpilot customer reviews. We illustrate how traders profit and loss can be negatively affected by brokers platform technical issues such as not being able to close profitable trades, closing trades with delays, disappearance of trades, disappearance of profit from clients statements, profit and loss discrepancies, stop loss not being triggered, stop loss or limit order triggered too early. Although regulatory bodies try to ensure that consumers get a fair deal, these attempts are hugely insufficient in protecting retail traders. Therefore, regulatory bodies such as the FCA should take these technical issues seriously and not rely on brokers internal investigations, because under any other circumstances, these platform manipulations would be considered as crimes and connivingly misappropriating funds.
Modeling and managing portfolio risk is perhaps the most important step to achieve growing and preserving investment performance. Within the modern portfolio construction framework that built on Markowitzs theory, the covariance matrix of stock retur ns is required to model the portfolio risk. Traditional approaches to estimate the covariance matrix are based on human designed risk factors, which often requires tremendous time and effort to design better risk factors to improve the covariance estimation. In this work, we formulate the quest of mining risk factors as a learning problem and propose a deep learning solution to effectively design risk factors with neural networks. The learning objective is carefully set to ensure the learned risk factors are effective in explaining stock returns as well as have desired orthogonality and stability. Our experiments on the stock market data demonstrate the effectiveness of the proposed method: our method can obtain $1.9%$ higher explained variance measured by $R^2$ and also reduce the risk of a global minimum variance portfolio. Incremental analysis further supports our design of both the architecture and the learning objective.
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).
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا