Abstract:Forecasting is a common data science task that helps organizations with capacity planning, goal setting, and anomaly detection. Despite its importance, there are serious challenges associated with producing reliable and high quality forecastsespecially when there are a variety of time series and analysts with expertise in time series modeling are relatively rare. To address these challenges, we describe a practical approach to forecasting "at scale" that combines configurable models with analyst-in-the-loop pe… Show more
“…In our seasonal decomposition step, we use TBATS as a deseasonalisation technique to extract the relevant seasonal components of a time series. We perform the seasonal extraction after fitting the TBATS model using the tbats function provided by the forecast package [33], [34] in R. 4) Prophet: Prophet is an automated forecasting framework developed by Taylor and Letham [37]. The main aim of this framework is to address the challenges involved in forecasting at Facebook, the employer of those authors at that time.…”
Section: Seasonal Decompositionmentioning
confidence: 99%
“…We compare our developments against a collection of current state-of-the-art techniques in forecasting with multiple seasonal cycles. This includes Tbats [18], Prophet [37], and FFORMA [51]. We also use two variants of Dynamic-Harmonic-Regression [33] as the benchmarks.…”
Section: E Benchmarks and Lstm-msnet Variantsmentioning
Generating forecasts for time series with multiple seasonal cycles is an important use-case for many industries nowadays. Accounting for the multi-seasonal patterns becomes necessary to generate more accurate and meaningful forecasts in these contexts. In this paper, we propose Long Short-Term Memory Multi-Seasonal Net (LSTM-MSNet), a decompositionbased, unified prediction framework to forecast time series with multiple seasonal patterns. The current state of the art in this space are typically univariate methods, in which the model parameters of each time series are estimated independently. Consequently, these models are unable to include key patterns and structures that may be shared by a collection of time series. In contrast, LSTM-MSNet is a globally trained Long Short-Term Memory network (LSTM), where a single prediction model is built across all the available time series to exploit the crossseries knowledge in a group of related time series. Furthermore, our methodology combines a series of state-of-the-art multiseasonal decomposition techniques to supplement the LSTM learning procedure. In our experiments, we are able to show that on datasets from disparate data sources, like e.g. the popular M4 forecasting competition, a decomposition step is beneficial, whereas in the common real-world situation of homogeneous series from a single application, exogenous seasonal variables or no seasonal preprocessing at all are better choices. All options are readily included in the framework and allow us to achieve competitive results for both cases, outperforming many state-ofthe-art multi-seasonal forecasting methods.
“…In our seasonal decomposition step, we use TBATS as a deseasonalisation technique to extract the relevant seasonal components of a time series. We perform the seasonal extraction after fitting the TBATS model using the tbats function provided by the forecast package [33], [34] in R. 4) Prophet: Prophet is an automated forecasting framework developed by Taylor and Letham [37]. The main aim of this framework is to address the challenges involved in forecasting at Facebook, the employer of those authors at that time.…”
Section: Seasonal Decompositionmentioning
confidence: 99%
“…We compare our developments against a collection of current state-of-the-art techniques in forecasting with multiple seasonal cycles. This includes Tbats [18], Prophet [37], and FFORMA [51]. We also use two variants of Dynamic-Harmonic-Regression [33] as the benchmarks.…”
Section: E Benchmarks and Lstm-msnet Variantsmentioning
Generating forecasts for time series with multiple seasonal cycles is an important use-case for many industries nowadays. Accounting for the multi-seasonal patterns becomes necessary to generate more accurate and meaningful forecasts in these contexts. In this paper, we propose Long Short-Term Memory Multi-Seasonal Net (LSTM-MSNet), a decompositionbased, unified prediction framework to forecast time series with multiple seasonal patterns. The current state of the art in this space are typically univariate methods, in which the model parameters of each time series are estimated independently. Consequently, these models are unable to include key patterns and structures that may be shared by a collection of time series. In contrast, LSTM-MSNet is a globally trained Long Short-Term Memory network (LSTM), where a single prediction model is built across all the available time series to exploit the crossseries knowledge in a group of related time series. Furthermore, our methodology combines a series of state-of-the-art multiseasonal decomposition techniques to supplement the LSTM learning procedure. In our experiments, we are able to show that on datasets from disparate data sources, like e.g. the popular M4 forecasting competition, a decomposition step is beneficial, whereas in the common real-world situation of homogeneous series from a single application, exogenous seasonal variables or no seasonal preprocessing at all are better choices. All options are readily included in the framework and allow us to achieve competitive results for both cases, outperforming many state-ofthe-art multi-seasonal forecasting methods.
“…(2) Prophet: Prophet [20] is a Bayesian nonlinear univariate generative model for time series forecasting which was proposed by Facebook in 2018. Like our method, Prophet is also a structural time series analysis method, which explicitly models the trend, seasonality, and event effects.…”
Section: A Experimental Setup and Baselinesmentioning
Multivariate time series are routinely encountered in real-world applications, and in many cases, these time series are strongly correlated. In this paper, we present a deep learning structural time series model which can (i) handle correlated multivariate time series input, and (ii) forecast the targeted temporal sequence by explicitly learning/extracting the trend, seasonality, and event components. The trend is learned via a 1D and 2D temporal CNN and LSTM hierarchical neural net. The CNN-LSTM architecture can (i) seamlessly leverage the dependency among multiple correlated time series in a natural way, (ii) extract the weighted differencing feature for better trend learning, and (iii) memorize the long-term sequential pattern. The seasonality component is approximated via a non-liner function of a set of Fourier terms, and the event components are learned by a simple linear function of regressor encoding the event dates. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of time series data sets, such as forecasts of Amazon AWS Simple Storage Service (S3) and Elastic Compute Cloud (EC2) billings, and the closing prices for corporate stocks in the same category.
“…It is also possible that long-term seasonal, day of week, and time of day effects can influence the outcome of N-of-1 studies. Future versions of our model may incorporate parameters for these effects and fit them using methods akin to those of Prophet [15] or other Bayesian time-series models.…”
Section: Study Limitations and Future Workmentioning
Recent advances in molecular biology, sensors, and digital medicine have led to an explosion of products and services for high-resolution monitoring of individual health.The N-of-1 study has emerged as an important methodological tool for harnessing these new data sources, enabling researchers to compare the effectiveness of health interventions at the level of a single individual. We have developed a stochastic time series model that simulates an N-of-1 study, facilitating rapid optimization of N-of-1 study designs and increasing the likelihood of study success while minimizing participant burden. Using simulation, we demonstrate how the number of treatment blocks, ordering of treatments within blocks, duration of each treatment, and sampling frequency affect our ability to detect true differences in treatment efficacy. We provide a set of recommendations for study designs based on treatment, outcome, and instrument parameters, and provide our simulation software as a supplement to the paper.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.