Collaborating Authors

Forecasting with Multiple Seasonality Machine Learning

An emerging number of modern applications involve forecasting time series data that exhibit both short-time dynamics and long-time seasonality. Specifically, time series with multiple seasonality is a difficult task with comparatively fewer discussions. In this paper, we propose a two-stage method for time series with multiple seasonality, which does not require pre-determined seasonality periods. In the first stage, we generalize the classical seasonal autoregressive moving average (ARMA) model in multiple seasonality regime. In the second stage, we utilize an appropriate criterion for lag order selection. Simulation and empirical studies show the excellent predictive performance of our method, especially compared to a recently popular `Facebook Prophet' model for time series.

What's the Secret to a Successful Seasonal SEO Strategy?


Seasonality is something that most businesses deal with on an annual basis. Whether it's actual physical seasons or holidays, different times of year bring unique needs and demands. This is even true with something as technical as SEO. We account for seasonality in almost every other aspect of business, so why wouldn't we think about it regarding SEO? Seasonal SEO isn't all that different from traditional SEO - it just takes specific time periods into account. There are a couple different types of seasonal SEO.

LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns Machine Learning

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

Understanding Time Series with R - KDnuggets


Analyzing time series can be an extremely useful resource for virtually any business, therefore, it is extremely important for data scientists entering the field to have a solid foundation on the main concepts. Luckily, a time series can be decomposed into its different elements and the decomposition of the process allows us to understand each of the parts that play a role in the analysis as a logical component of the whole system. While it is true that R has already many powerful packages to analyze time series, in this article the goal is to perform a time series analysis --specifically for forecasting-- by building a function from scratch to analyze each of the different elements in the process. There are several methods to do forecasting, but in this article, we'll focus on the multiplicative time series approach, in which we have the following elements: Seasonality: It consists of variations that occur at regular intervals, for example, every quarter, on summer vacation, at the end of the year, etc. A clear example would be higher conversion rates on gym memberships in January or a spike in video game sales around the holidays.