|
on Financial Markets |
|
Issue of 2018‒08‒20
three papers chosen by |
| By: | Phil Maguire; Karl Moffett; Rebecca Maguire |
| Abstract: | Smart beta, also known as strategic beta or factor investing, is the idea of selecting an investment portfolio in a simple rule-based manner that systematically captures market inefficiencies, thereby enhancing risk-adjusted returns above capitalization-weighted benchmarks. We explore the idea of applying a smart strategy in reverse, yielding a "bad beta" portfolio which can be shorted, thus allowing long and short positions on independent smart beta strategies to generate beta neutral returns. In this article we detail the construction of a monthly reweighted portfolio involving two independent smart beta strategies; the first component is a long-short beta-neutral strategy derived from running an adaptive boosting classifier on a suite of momentum indicators. The second component is a minimized volatility portfolio which exploits the observation that low-volatility stocks tend to yield higher risk-adjusted returns than high-volatility stocks. Working off a market benchmark Sharpe Ratio of 0.42, we find that the market neutral component achieves a ratio of 0.61, the low volatility approach achieves a ratio of 0.90, while the combined leveraged strategy achieves a ratio of 0.96. In six months of live trading, the combined strategy achieved a Sharpe Ratio of 1.35. These results reinforce the effectiveness of smart beta strategies, and demonstrate that combining multiple strategies simultaneously can yield better performance than that achieved by any single component in isolation. |
| Date: | 2018–08 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1808.02505&r=fmk |
| By: | Hyeong Kyu Choi |
| Abstract: | Predicting the price correlation of two assets for future time periods is important in portfolio optimization. We apply LSTM recurrent neural networks (RNN) in predicting the stock price correlation coefficient of two individual stocks. RNNs are competent in understanding temporal dependencies. The use of LSTM cells further enhances its long term predictive properties. To encompass both linearity and nonlinearity in the model, we adopt the ARIMA model as well. The ARIMA model filters linear tendencies in the data and passes on the residual value to the LSTM model. The ARIMA LSTM hybrid model is tested against other traditional predictive financial models such as the full historical model, constant correlation model, single index model and the multi group model. In our empirical study, the predictive ability of the ARIMA-LSTM model turned out superior to all other financial models by a significant scale. Our work implies that it is worth considering the ARIMA LSTM model to forecast correlation coefficient for portfolio optimization. |
| Date: | 2018–08 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1808.01560&r=fmk |
| By: | Colliard, Jean-Edouard; Foucault, Thierry; Hoffmann, Peter |
| Abstract: | We propose a new model of interdealer trading. Dealers trade together to reduce their inventory holding costs. Core dealers share these costs efficiently and provide liquidity to peripheral dealers, who have heterogeneous access to core dealers. We derive predictions about the effects of peripheral dealers’ connectedness to core dealers and the allocation of aggregate inventories between core and peripheral dealers on the distribution of interdealer prices, the efficiency of interdealer trades, and trading costs for the dealers’ clients. For instance, the dispersion of interdealer prices is higher when fewer peripheral dealers are connected to core dealers or when their aggregate inventory is higher. |
| Keywords: | OTC markets; Interdealer trading; Inventory management |
| JEL: | G00 |
| Date: | 2018–07–10 |
| URL: | http://d.repec.org/n?u=RePEc:ebg:heccah:1286&r=fmk |