Prescriptive analytics focuses on finding the best course of action in a scenario, given the available data. It’s related to both descriptive analytics and predictive analytics, but emphasizes actionable insights instead of data monitoring.
Artificial Intelligence and Machine Learning is the Foundation
Prescriptive Analysis uses the information provided by Descriptive Analytics and Predictive Analytics. There are two possible approaches in this type of Analytics: one based on heuristics (systems based on BRMS and one based on operational research techniques. In the Artificial Intelligence field, the different analytical techniques provide more and more intelligence and business efficiency. The most basic, Descriptive Analytics, provides information and knowledge of the business. Predictive Analytics predicts events and allows to anticipate them. And the most advanced, Prescriptive Analytics, gives the ability to automate decision making.
It heavily relies on artificial intelligence techniques, such as machine learning—the ability of a computer program, without additional human input, to understand and advance from the data it acquires, adapting all the while. Machine learning makes it possible to process a tremendous amount of data available today. As new or additional data becomes available, computer programs adjust automatically to make use of it, in a process that is much faster and more comprehensive than human capabilities could manage. Specifically, prescriptive analytics factors information about possible situations or scenarios, available resources, past performance, and current performance, and suggests a course of action or strategy. It can be used to make decisions on any time horizon, from immediate to long term.
Prescriptive analytics can help organizations make decisions based on highly analyzed facts rather than jump to under-informed conclusions based on instinct. Prescriptive analytics can simulate the probability of various outcomes and show the probability of each, helping organizations to better understand the level of risk and uncertainty they face than they could be relying on averages. Organizations can gain a better understanding of the likelihood of worst-case scenarios and plan accordingly. It could also be used to evaluate whether a local fire department should require residents to evacuate a particular area when a wildfire is burning nearby. It could also be used to predict whether an article on a particular topic will be popular with readers based on data about searches and social shares for related topics. Another use could be to adjust a worker training program in real-time based on how the worker is responding to each lesson.
Energy and Unconventional Resource Development
Marketers, operations experts, financial officers and other business leaders have already used prescriptive analytics to improve customer experience, reduce churn, increase up-selling and cross-selling revenue, streamline logistics and enhance other important applications. For the oil and gas industry, prescriptive analytics can help locate fields with the richest concentrations of oil and gas, make pipelines safer, and improve the fracking process for greater output and fewer threats to the environment.
More than 95 percent of the world’s data today is unstructured videos, images, sounds and texts. Until recently, most big data analytics technologies looked only at numbers. The oil and gas industry looked at images and numbers, but in separate silos. However, the ability to analyze hybrid data a combination unstructured and structured data provides a much clearer and more complete picture of the current and future problems and opportunities, along with the best actions to achieve the desired outcomes.
Taking hybrid data into account is critical because of the multi-billion dollar investment and drilling decisions that are being made by the energy companies regarding where to drill, where to frack and how to frack. It calls for combining disparate computational and scientific disciplines to be able to interpret different types of data together. For example, to algorithmically interpret images (such as well logs), machine learning needs to be combined with pattern recognition, computer vision and image processing. Mixing these different disciplines provides more holistic recommendations regarding where and how to drill and frack, while reducing the chances of problems that could emerge along the way. Another potential application of prescriptive analytics is that it can possibly predict corrosion development or cracks in pipelines and prescribe preventive and preemptive actions by analyzing video data from cameras along with other data from robotic devices called “smart pigs” inside these pipelines.
Prescriptive Analysis in Healthcare
Prescriptive analytics facilitates hospitals in cutting costs, delivering better services, and improving transparency in their day-to-day functioning. Prescriptive analytics can also benefit health insurers and pharmaceutical companies. Insurance companies can use it to provide pricing and premium information to their clients, while pharmaceutical companies can use it to accelerate the speed of developing drugs and getting faster approvals. The onus lies on these healthcare companies on how they leverage it to improve their services and offerings. In the end, it is all about delivering the best possible care to patients.
To understand how prescriptive analytics can help healthcare companies, let’s take an example of patients with diabetes, a health insurance company might find out from its data that a significant number of diabetics are prone to diabetic retinopathy. They can use prescriptive analytics to analyze if there will be an increase in ophthalmology claims in the next year. This will help them to determine if they should keep the average ophthalmology reimbursement rates the same, increase, or decrease it by next year. It enables them to make more informed decisions.
Another advantage of prescriptive analytics is that it prepares the healthcare companies for future and unforeseen events. For example, let’s take a hypothetical situation of COVID-19. The hospitals know from historical and real-time data people with pre-existing diseases and old-aged patients are more susceptible to infections. This will enable the hospitals to provide topmost care to the vulnerable category of patients. It will also help the hospitals to trace the doctors and nurses who provide care to the patients and ensure that they follow the guidelines laid down by the Government and the World Health Organization (WHO) to avoid getting infected or spreading infection. It helps healthcare companies to mitigate further risks.
The benefit of prescriptive analytics is that it goes a step ahead of the predictive model that hospitals usually use. If predictive analytics helps a healthcare company to forecast future outcomes, prescriptive analytics nudges it to take action on those findings. It gives the healthcare company the power to influence the results. With prescriptive analytics, doctors can understand the patient holistically, find out the associated risks, and then determine what interventions could help in the patient’s recovery. Prescriptive analytics removes all the guesswork from the decision-making process and optimizes it to provide more improved care to its patients.
Image Processing, Industrial Intelligence and Computation
The image and video analytics science has scaled with advances in machine vision, multi-lingual speech recognition and rules-based decision engines. Intense interest exists in prescriptive analytics driven by real-time streams of rich image and video content. Consumers with mobile devices drive an explosion of location-tracked image and video data. The human brain simultaneously processes millions of images, movement, sound and other esoteric information from multiple sources. The brain is exceptionally efficient and effective in its capacity to prescribe and direct a course of action and eclipses any computing power available today. Smartphones now record and share images, audios and videos at an incredibly increasing rate, forcing our brains to process more.
Image analytics is the automatic algorithmic extraction and logical analysis of information found in image data using digital image processing techniques. The use of bar codes and QR codes are simple examples, but interesting examples are as complex as facial recognition and position and movement analysis. Today, images and image sequences (videos) make up about 80 percent of all corporate and public unstructured big data. As growth of unstructured data increases, analytical systems must assimilate and interpret images and videos as well as they interpret structured data such as text and numbers. To a computer, images are either a raster image or a vector image. Simply put, raster images are a sequence of pixels with discreet numerical values for color; vector images are a set of color-annotated polygons. To perform analytics on images or videos, the geometric encoding must be transformed into constructs depicting physical features, objects and movement represented by the image or video. These constructs can then be logically analyzed by a computer. The process of transforming big data into higher-level constructs that can be analyzed is organized in progressive steps that each adds value to the original information in a value chain. Prescriptive analytics leverages the emergence of big data and computational and scientific advances in the fields of statistics, mathematics, operations research, business rules and machine learning.
A process-intensive task, the prescriptive approach analyzes potential decisions, the interactions between decisions, the influences that bear upon these decisions and the bearing all of the above has on an outcome to ultimately prescribe an optimal course of action in real time. Prescriptive analytics is not fail proof, however, but is subject to the same distortions that can upend descriptive and predictive analytics, including data limitations and unaccounted-for external forces. The effectiveness of predictive analytics also depends on how well the decision model captures the impact of the decisions being analyzed.
Prescriptive analytics can also suggest decision options for how to take advantage of a future opportunity or mitigate a future risk, and illustrate the implications of each decision option. In practice, prescriptive analytics can continually and automatically process new data to improve the accuracy of predictions and provide better decision options.