Challenges for Context-Driven Time Series Forecasting

Abstract

Predicting time series is a crucial task for organizations, since decisions are often based on uncertain information. Many forecasting models are designed from a generic statistical point of view. However, each real-world application requires domain-specific adaptations to obtain high-quality results. All such specifics are summarized by the term of context. In contrast to current approaches, we want to integrate context as the primary driver in the forecasting process. We introduce context-driven time series forecasting focusing on two exemplary domains: renewable energy and sparse sales data. In view of this, we discuss the challenge of context integration in the individual process steps.

Development of Usability Enhancement Model for Unstructured Big Data Using SLR

“…It includes lexicon-based and learning-based techniques such as information extraction, summarization, clustering, visualization, and categorization [17], [18]. The general process of text analysis starts with the data collection and preparation for analysis where data is transformed into a usable format [19]- [21]. The information extraction (IE) process extracts useful structured information from the unstructured data in the form of entities, relations, objects, events, and certain other types.…”

“…Each usability issue with challenges has been presented in Table 6. [11], finding the right data [24] [70], variation in perspectives [24], concept identification [71], insufficient structural metadata [72] [81], lack of dynamic context [19], data complexity [64], diversity [53], and uncertainty [66] Completeness Contextual variability of relationships [67], usability and semantic relationship [54], inherent precision and uncertainty factors [73], data causality issues [55], structural ambiguities text [56] [58], readability [57], lack of structure [68] [32] [74] [80], structural differences [60], and data incompleteness [11] 2) KEY PROCESSES…”

“…Various structures have been identified as structural usability determinants in this study, as shown in Figure 12. These include criteria specific index structures [81], flexible schema with dynamic context [19], syntactic structure [64] [54] [56], lexical structure [54], lattice structure [68], latent structure [80], and logical structure [58].…”