A hybrid machine learning model for forecasting a billing period’s peak electric load days

Many models have been studied for forecasting the peak electric load, but studies focusing on forecasting peak electric load days for a billing period are scarce. This focus is highly relevant to consumers, as their electricity costs are determined based not only on total consumption, but also on the peak load required during a period. Forecasting these peak days accurately allows demand response actions to be planned and executed efficiently in order to mitigate these peaks and their associated costs. We propose a hybrid model based on ARIMA, logistic regression and artificial neural networks models. This hybrid model evaluates the individual results of these statistical and machine learning models in order to forecast whether a given day will be a peak load day for the billing period. The proposed model predicted 70% (40/57) of actual peak load days accurately and revealed potential savings of approximately USD $80,000 for an American university during a one-year testing period.     

Volatility of volatility is (also) rough

Using high-frequency data for major volatility indexes, we compute the volatility of volatility and show that its logarithm follows a fractional Brownian motion with Hurst parameter smaller than 1/2 thereby extending to the volatility asset class the recent findings obtained for the equity index markets. The results confirm that the volatility of volatility is a rough process and it possesses the long memory property. We also show that the correlation between the volatility and the volatility of volatility is positive, consistent with observations in the volatility option market. Lastly, a robustness check using volatility futures confirms the findings.     

寡头博弈模型中的时间记忆性质与预期对模型稳定性的影响

公平竞争是市场经济的灵魂,是发挥市场力量的关键.研究寡头垄断企业的竞争行为和竞争环境对中国强化反垄断,构建更加安全公平、有效竞争的经济市场意义重大.梳理寡头垄断企业中的价格竞争和产量竞争中的模型稳定性研究情况,通过模型的边界均衡点和局部均衡点来分析模型的稳定性,对寡头博弈模型中时间的记忆性与预期对模型稳定性的影响进行分析.     

Parameter risk in time-series mortality forecasts

The projection of mortality rates is an essential part of valuing liabilities in life insurance portfolios and pension schemes. An important tool for risk management and solvency purposes is a stochastic projection model. We show that ARIMA models can be better representations of mortality time-series than simple random-walk models. We also consider the issue of parameter risk in time-series models from the point of view of an insurer using them for regulatory risk reporting – formulae are given for decomposing overall risk into undiversifiable trend risk (parameter uncertainty) and diversifiable volatility. Particular attention is given to the contrasts in how academic researchers might view these models and how insurance regulators and practitioners in life offices might use them. Using a bootstrap method we find that, while certain kinds of parameter risk are negligible, others are too material to ignore. We also find that an objective model selection criterion, such as goodness of fit to past data, can result in the selection of a model with unstable parameter values. While this aspect of the model is superficially undesirable, it also leads to slightly higher capital requirements and thus makes the model of keen interest to regulators. Our conclusions have relevance to insurers using value-at-risk capital assessments in the European Union under Solvency II, but also territories using conditional tail expectations such as Australia, Canada and Switzerland.     

阶梯电价政策的居民节能意愿与节能效果评估--基于广东案例的研究

以广东省为例,基于粤东、粤西、粤北及珠三角典型地市的社会调查,统计分析阶梯电价政策对居民节能意愿及家庭用电的影响;同时运用广东省月度电力数据,构建ARIMA模型,定量研究政策实施的节能效果。研究表明,阶梯电价政策的实施对改善居民节能意愿有积极影响,并在短期内有明显的节能效果,但随着时间推移,节能效果有所减弱。为设计与完善相关政策,未来需要从节能意愿、经济激励等角度切入,提升政策的针对性、有效性。     

黑龙江省生态足迹分析及ARIMA模型预测

为了解黑龙江省生态可持续发展问题,对黑龙江省生态足迹进行分析,并寻求动态预测结果。运用生态足迹模型对黑龙江省2000~2015年的人均生态足迹和生态承载力进行测算,在此基础上选用ARIMA模型,并结合使用Eviews软件对未来10年人均生态足迹和生态承载力进行预测。研究结果表明2000~2015年间黑龙江省人均生态足迹一直不断增加,人均生态承载力呈现波动缓慢上升的趋势,生态系统处于不安全状态;2016~2025年黑龙江省人均生态足迹仍然持续增大,虽然人均生态承载力也缓慢上升,但人均生态赤字仍然越来越大,黑龙江省生态安全面临巨大挑战。     

Short-term forecasting of Japanese tourist inflow to South Korea using Google trends data

We utilize the Internet search data from Google Trends to provide short-term forecasts for the inflow of Japanese tourists to South Korea. We construct the Google variable in a systematic way by combining keywords to minimize mean squared or mean absolute forecasting errors. We augment the Google variable to the standard time-series forecasting models and compare their forecasting accuracies. We find that Google-augmented models perform much better than the standard time-series models in terms of short-term forecasting accuracy. In particular, Google models show better out-of-sample forecasting performance than in-sample forecasting.     

Factors Influencing Organic and Fair Trade Coffee Growers Level of Engagement with Cooperatives: The Case of Coffee Farmers in Mexico

We study the factors influencing the percentage of organic and fair trade certified coffee sold through a cooperative by growers of five cooperatives in Mexico. The percentage of coffee sold through the cooperative was used as a proxy of growers’ engagement with a cooperative. Using factor analysis and a fractional probit regression, we evaluated the proposition that the level of engagement can be explained by transaction cost economics, social norms and connections, and farmer and farm business characteristics. We found that farm size, uncertainty regarding cooperative time of payment to the members and cooperative commitment on price to be paid negatively influence the level of engagement. In contrast, asset specificity, relational commitment, and price have a positive impact on engagement. Our results may help cooperatives and policy makers to build strategies aiming to increase this level of engagement. This is relevant because lower grower engagement has been found to be positively correlated with weak performing cooperatives.     

When was the U.S. housing downturn predictable? A comparison of univariate forecasting methods

This paper uses three classes of univariate time series techniques (ARIMA type models, switching regression models, and state-space/structural time series models) to forecast, on an ex post basis, the downturn in U.S. housing prices starting around 2006. The performance of the techniques is compared within each class and across classes by out-of-sample forecasts for a number of different forecast points prior to and during the downturn. Most forecasting models are able to predict a downturn in future home prices by mid 2006. Some state-space models can predict an impending downturn as early as June 2005. State-space/structural time series models tend to produce the most accurate forecasts, although they are not necessarily the models with the best in-sample fit.     

The characteristic function of rough Heston models

It has been recently shown that rough volatility models, where the volatility is driven by a fractional Brownian motion with small Hurst parameter, provide very relevant dynamics in order to reproduce the behavior of both historical and implied volatilities. However, due to the non‐Markovian nature of the fractional Brownian motion, they raise new issues when it comes to derivatives pricing. Using an original link between nearly unstable Hawkes processes and fractional volatility models, we compute the characteristic function of the log‐price in rough Heston models. In the classical Heston model, the characteristic function is expressed in terms of the solution of a Riccati equation. Here, we show that rough Heston models exhibit quite a similar structure, the Riccati equation being replaced by a fractional Riccati equation.