Interplay between Small Data and Big Data

Focusing on the area of data-driven insight, how can we leverage the data from sensors and devices to create meaningful mobile health experiences? Analyzing the data at an individual-level (small data) can facilitate behavior change and make people healthier by crafting effective engagement strategies. Analyzing the data at the population-level (big data) can empower providers to better identify at-risk populations and group patterns in order to guide better health and wellness decisions. Ultimately, combining small data and big data analysis in a synergistic and economic manner is even more compelling and enables the transformation of data into meaningful personalized experiences for consumers and providers. Integrating insight derived from population-level analysis into the analysis of small data can create insight that is not only focused on the individual alone, but also encapsulate social context around the individual. This synergistic interplay between small data and big data analysis has benefits not only from a computational perspective by offloading computation to the client, but also increases the types of insights that can be derived from data. Figure 1 outlines the general concept of insights that are derived and combined from small data and big data analysis.

Figure 1 Small Data and Big Data driven Insights

Figure 1 Small Data and Big Data driven Insights

Further, integrating 3rd party data sources (i.e. genetic, environmental, and IoT) and jointly analyzing small data and big data will further help to understand and exploit the data in new ways. Building effective consumer engagement strategies involves the proper application of theoretical behavior change models in combination with the right analytics framework, ranging from descriptive and predictive to prescriptive analytical models and their effective presentation.