ABSTRACT
Alternative data is data from non-traditional sources that can be used when making financial decisions. The success in the application of alternative data to finance means that businesses and traders are looking at such data and their applications to gain further insights. Sensors on all scales are used to obtain alternative data, from satellites in orbit which measure activity to personal devices determining location. This paper provides examples of sensor data and how it can be applied to the business world.
An introduction to sensor data is given and its different categories examined. Examples of satellite, geolocation and weather data are presented with an overview of current work and literature with an introductory methodology on how such data can be used in each case. An investigation is presented into classification techniques used for counting cars from satellite data and the application of such techniques to business decisions.
Geolocation data and its use in measuring consumer traffic both digitally and physically is examined using tools such as Google Gears and its application to financial decision making, for example, by hedge fund managers, is discussed. Sensors can also be used to measure foot traffic at physical business locations. Visual sensors can be used to generate a 3D map to measure the volume of customers with 90% accuracy.
The collection of weather data supports models in areas such as forecasting crop yield and calculating weather derivatives. An overview of current techniques is presented, how statistical models are formed from such data and how these models are applied. Additional sources of alternative data and their potential uses are presented to further demonstrate the wide applicability of sensor data. Further works and references are highlighted at the end.
