Prescriptive analytics: Difference between revisions

Revision as of 23:35, 1 June 2020

Latest revision as of 20:47, 23 June 2025

(35 intermediate revisions by 26 users not shown)

Line 1:

{{short description|Form of business analytics offering future decision options}}

'''Prescriptive analytics''' is the third and final phase of [[business analytics]], which also includes descriptive and [[Predictive analytics|predictive]] analytics.<ref>{{cite journal|author1=Evans, James R.|author2=Lindner, Carl H. |lastauthoramp=yes |title=Business Analytics: The Next Frontier for Decision Sciences|journal=Decision Line|date=March 2012|volume=43|issue=2}}</ref><ref name="LustigEtAl">http://www.analytics-magazine.org/november-december-2010/54-the-analytics-journey{{cite journal|last=Lustig,Irv, [[Brenda L. Dietrich|Dietrich, Brenda]], Johnson, Christer, and Dziekan, Christopher|title=The Analytics Journey|journal=Analytics|date=Nov–Dec 2010}}</ref>

'''Prescriptive analytics''' is a form of [[business analytics]] which suggests decision options for how to take advantage of a future opportunity or mitigate a future risk and shows the implication of each decision option. It enables an enterprise to consider "the best course of action to take" in the light of information derived from [[Descriptive statistics|descriptive]] and [[predictive analytics]].<ref name="basu">{{cite journal |last=Basu |first=Atanu |year=2019 |title=Five pillars of prescriptive analytics success |url=https://pubsonline.informs.org/do/10.1287/LYTX.2013.02.07/full/ |journal=The Analytics Journey |doi=10.1287/LYTX.2013.02.07 |s2cid=240957300|url-access=subscription }}</ref>

==Overview==

Referred to as the "final frontier of analytic capabilities,"<ref>{{Cite web |url=https://www.globys.com/2013/06/gartner-terms-prescriptive-analytics-%E2%80%9Cfinal-frontier%E2%80%9D-analytic-capabilities |title=Archived copy |access-date=2014-10-29 |archive-url=https://web.archive.org/web/20160402140918/http://globys.com/2013/06/gartner-terms-prescriptive-analytics-%E2%80%9Cfinal-frontier%E2%80%9D-analytic-capabilities |archive-date=2016-04-02 |url-status=dead }}</ref> prescriptive analytics entails the application of [[mathematical sciences|mathematical]] and [[computational science]]s and suggests decision options to take advantage of the results of descriptive and predictive analytics. The first stage of business analytics is descriptive analytics, which still accounts for the majority of all business analytics today.<ref>{{cite journal|last=Davenport,Tom |title=The three '..tives' of business analytics; predictive, prescriptive and descriptive|journal=CIO Enterprise Forum|date=November 2012}}</ref> Descriptive analytics looks at past performance and understands that performance by mining historical data to look for the reasons behind past success or failure. Most management reporting – such as [[sales]], [[marketing]], [[Business operations|operations]], and [[finance]] – uses this type of post-mortem analysis.

Prescriptive analytics is the third and final phase of business analytics, which also includes descriptive and predictive analytics.<ref>{{cite journal|author1=Evans, James R.|author2=Lindner, Carl H. |name-list-style=amp |title=Business Analytics: The Next Frontier for Decision Sciences|journal=Decision Line|date=March 2012|volume=43|issue=2}}</ref><ref name=":0">{{Cite journal |last1=Basu |first1=Atanu |last2=Brown |first2=Scott |last3=Worth |first3=Tim |date=2019-10-25 |title=Predictive analytics in field service |url=http://pubsonline.informs.org/do/10.1287/LYTX.2010.06.03/full/ |journal=The Analytics Journey |language=en |doi=10.1287/lytx.2010.06.03|s2cid=242347282 |url-access=subscription }}</ref> Referred to as the "final frontier of analytic capabilities",<ref>{{Cite web |url=https://www.globys.com/2013/06/gartner-terms-prescriptive-analytics-%E2%80%9Cfinal-frontier%E2%80%9D-analytic-capabilities |title=Gartner terms Prescriptive Analytics as the "Final Frontier" of Analytic Capabilities &#124; Globys.com |access-date=2014-10-29 |archive-url=https://web.archive.org/web/20160402140918/http://globys.com/2013/06/gartner-terms-prescriptive-analytics-%E2%80%9Cfinal-frontier%E2%80%9D-analytic-capabilities |archive-date=2016-04-02 |url-status=dead }}</ref> prescriptive analytics entails the application of [[mathematical sciences|mathematical]] and [[computational science]]s and suggests decision options for how to take advantage of the results of descriptive and predictive phases.

Referred to as the "final frontier of analytic capabilities,"<ref>{{Cite web |url=https://www.globys.com/2013/06/gartner-terms-prescriptive-analytics-%E2%80%9Cfinal-frontier%E2%80%9D-analytic-capabilities |title=Archived copy |access-date=2014-10-29 |archive-url=https://web.archive.org/web/20160402140918/http://globys.com/2013/06/gartner-terms-prescriptive-analytics-%E2%80%9Cfinal-frontier%E2%80%9D-analytic-capabilities |archive-date=2016-04-02 |url-status=dead }}</ref> prescriptive analytics entails the application of [[mathematical sciences|mathematical]] and [[computational science]]s and suggests decision options to take advantage of the results of descriptive and predictive analytics. The first stage of business analytics is descriptive analytics, which still accounts for the majority of all business analytics today.<ref>{{cite journal|last=Davenport, Tom |title=The three '..tives' of business analytics; predictive, prescriptive and descriptive|journal=CIO Enterprise Forum|date=November 2012}}</ref> Descriptive analytics looks at past performance and understands that performance by mining historical data to look for the reasons behind past success or failure. Most management reporting – such as [[sales]], [[marketing]], [[Business operations|operations]], and [[finance]] – uses this type of post-mortem analysis.

[[File:Three Phases of Analytics.png|thumb|left|350px|Prescriptive Analytics extends beyond predictive analytics by specifying both the actions necessary to achieve predicted outcomes, and the interrelated effects of each decision]]The next phase is [[predictive analytics]]. Predictive analytics answers the question what is likely to happen. This is when historical data is combined with rules, [[algorithms]], and occasionally external data to determine the probable future outcome of an event or the likelihood of a situation occurring. The final phase is prescriptive analytics,<ref>{{cite journal|last1=Haas|first1=Peter J.|author1-link=Peter J. Haas (computer scientist)|last2=Maglio|first2=Paul P.|last3=Selinger|first3=Patricia G.|author3-link=Patricia Selinger|last4=Tan|first4=Wang-Chie|issue=12|journal=Proceedings of the VLDB Endowment|title=Data is Dead…Without What-If Models|volume=4|year=2011}}</ref> which goes beyond predicting future outcomes by also suggesting actions to benefit from the predictions and showing the implications of each decision option.<ref>{{cite journal|author1=Stewart, Thomas. R. |author2=McMillan, Claude, Jr. |lastauthoramp=yes |title=Descriptive and Prescriptive Models for Judgment and Decision Making: Implications for Knowledge Engineering|journal=NATO AS1 Senes, Expert Judgment and Expert Systems|year=1987|volume=F35|pages=314–318}}</ref>

[[File:Three Phases of Analytics.png|thumb|right|Prescriptive Analytics extends beyond predictive analytics by specifying both the actions necessary to achieve predicted outcomes, and the interrelated effects of each decision.]]

Prescriptive analytics not only anticipates what will happen and when it will happen, but also why it will happen<!-- There is no evidence nor citation supporting this statement. Furthermore, if prescriptive analytics analytics "not only anticipates what will happen and when it will happen, but also why it will happen, then what is the role of predictive modelling, forecasting and causal modelling? -->. Further, prescriptive analytics suggests decision options on how to take advantage of a future opportunity or mitigate a future risk and shows the implication of each decision option. Prescriptive analytics can continually take in new data to re-predict and re-prescribe, thus automatically improving prediction accuracy<!-- This lacks evidence and supporting citation. It does not follow that prediction accuracy improves as a result of re-predicting. --> and prescribing better decision options. Prescriptive analytics ingests hybrid data, a combination of structured (numbers, categories) and unstructured data (videos, images, sounds, texts), and business rules to predict what lies ahead and to prescribe how to take advantage of this predicted future without compromising other priorities.<ref>{{cite journal |last1=Riabacke |first1=Mona |last2=Danielson |first2=Mats |last3=Ekenberg |first3=Love |title=State-of-the-Art Prescriptive Criteria Weight Elicitation |journal=Advances in Decision Sciences |date=30 December 2012 |volume=2012 |pages=1–24 |doi=10.1155/2012/276584 }}</ref>

The next phase is predictive analytics. Predictive analytics answers the question of what is likely to happen. This is where historical data is combined with rules, [[algorithms]], and occasionally external data to determine the probable future outcome of an event or the likelihood of a situation occurring.

[[File:Three Phases of Analytics.png|thumb|left|350px|Prescriptive Analytics extends beyond predictive analytics by specifying both the actions necessary to achieve predicted outcomes, and the interrelated effects of each decision]]The next phase is [[predictive analytics]]. Predictive analytics answers the question what is likely to happen. This is when historical data is combined with rules, [[algorithms]], and occasionally external data to determine the probable future outcome of an event or the likelihood of a situation occurring. The final phase is prescriptive analytics,<ref>{{cite journal|last1=Haas|first1=Peter J.|author1-link=Peter J. Haas (computer scientist)|last2=Maglio|first2=Paul P.|last3=Selinger|first3=Patricia G.|author3-link=Patricia Selinger|last4=Tan|first4=Wang-Chie|issue=12|journal=Proceedings of the VLDB Endowment|title=Data is Dead…Without What-If Models|volume=4|year=2011|pages=1486–1489|doi=10.14778/3402755.3402802|s2cid=6239043|doi-access=free}}</ref> which goes beyond predicting future outcomes bybut also suggesting actions to benefit from the predictions and showing the implications of each decision option.<ref>{{cite journal |author1=Stewart, Thomas. R. |author2=McMillan, Claude, Jr. |name-list-style=amp |lastauthorampyear=yes1987 |title=Descriptive and Prescriptive Models for Judgment and Decision Making: Implications for Knowledge Engineering |journal=NATO AS1 Senes, Expert Judgment and Expert Systems|year=1987 |volume=NATO AS1 Subseries F35 |pages=314–318}}</ref>

All three phases of analytics can be performed through professional services or technology or a combination. In order to scale, prescriptive analytics technologies need to be adaptive to take into account the growing volume, velocity, and variety of data that most mission critical processes and their environments may produce.

Prescriptive analytics notuses onlyalgorithms anticipatesand whatmachine willlearning happenmodels andto whensimulate itvarious willscenarios happen,and butpredict alsothe whylikely itoutcomes willof happendifferent decisions.<!ref name=":1">{{Citation |last1=Soltanpoor |first1=Reza |title=Prescriptive Analytics for Big Data |date=2016 |url=http://link.springer.com/10.1007/978-3-319-46922-5_19 There|work=Databases isTheory noand evidenceApplications nor|volume=9877 citation|pages=245–256 supporting|editor-last=Cheema this|editor-first=Muhammad statementAamir |access-date=2023-05-01 |place=Cham |publisher=Springer International Publishing |doi=10.1007/978-3-319-46922-5_19 Furthermore,|isbn=978-3-319-46921-8 if|last2=Sellis prescriptive|first2=Timos analytics|series=Lecture Notes in Computer Science |editor2-last=Zhang |editor2-first=Wenjie |editor3-last=Chang |editor3-first=Lijun|url-access=subscription }}</ref> It then suggests the best course of action based on the desired outcome and the constraints of the situation. Prescriptive analytics "not only anticipates what will happen and when it will happen, but also why it will happen,.<ref thenname=":1" what is the role of predictive modelling, forecasting and causal modelling? --/>. Further, prescriptive analytics suggests decision options on how to take advantage of a future opportunity or mitigate a future risk and shows the implication of each decision option. Prescriptive analytics incorporates both [[structured data|structured]] and [[unstructured data]], and uses a combination of advanced analytic techniques and disciplines to predict, prescribe, and adapt. It can continually take in new data to re-predict and re-prescribe, thus automatically improving prediction accuracy<!-- This lacks evidence and supporting citation. It does not follow that prediction accuracy improves as a result of re-predicting. --> and prescribing better decision options. PrescriptiveEffective prescriptive analytics ingestsutilises hybrid data, a combination of structured (numbers, categories) and unstructured data (videos, images, sounds, texts), and business rules to predict what lies ahead and to prescribe how to take advantage of this predicted future without compromising other priorities.<ref>{{cite journal |last1=Riabacke |first1=Mona |last2=Danielson |first2=Mats |last3=Ekenberg |first3=Love |title=State-of-the-Art Prescriptive Criteria Weight Elicitation |journal=Advances in Decision Sciences |date=30 December 2012 |volume=2012 |pages=1–24 |doi=10.1155/2012/276584 |doi-access=free }}</ref> Basu suggests that without hybrid data input, the benefits of prescriptive analytics are limited.<ref name="basu" />{{efn|Atanu Basu is the CEO and president of Ayata.<ref name=basu />}}

One criticism of prescriptive analytics is that its distinction from [[predictive analytics]] is ill-defined and therefore ill-conceived.<ref>{{cite journal|last=Bill Vorhies|url=http://www.predictiveanalyticsworld.com/patimes/prescriptive-versus-predictive-analytics-distinction-without-difference/ |title=Prescriptive versus Predictive Analytics – A Distinction without a Difference?|journal=Predictive Analytics Times|date=November 2014}}</ref> [[File:Components of Prescriptive Analytics.png|thumb|600px|The scientific disciplines that comprise Prescriptive Analytics]]

In addition to this variety of data types and growing data volume, incoming data can also evolve with respect to velocity, that is, more data being generated at a faster or a variable pace. Business rules define the [[business process]] and include objectives constraints, preferences, policies, best practices, and boundaries. Mathematical models and computational models are techniques derived from mathematical sciences, computer science and related disciplines such as applied statistics, machine learning, [[operations research]], [[natural language processing]], [[computer vision]], pattern recognition, image processing, [[speech recognition]], and signal processing. The correct application of all these methods and the verification of their results implies the need for resources on a massive scale including human, computational and temporal for every Prescriptive Analytic project. In order to spare the expense of dozens of people, high performance machines and weeks of work one must consider the reduction of resources and therefore a reduction in the accuracy or reliability of the outcome. The preferable route is a reduction that produces a probabilistic result within acceptable limits.{{factcitation needed|date=May 2020}}

All three phases of analytics can be performed through professional services or technology or a combination. In order to scale, prescriptive analytics technologies need to be adaptive to take into account the growing volume, velocity, and variety of data that most mission critical processes and their environments may produce.

One criticism of prescriptive analytics is that its distinction from [[predictive analytics]] is ill-defined and therefore ill-conceived.<ref>{{cite journal|last=Bill Vorhies|url=http://www.predictiveanalyticsworld.com/patimes/prescriptive-versus-predictive-analytics-distinction-without-difference/ |title=Prescriptive versus Predictive Analytics – A Distinction without a Difference?|journal=Predictive Analytics Times|date=November 2014}}</ref> [[File:Components of Prescriptive Analytics.png|thumb|600pxright|The scientific disciplines that comprise Prescriptive Analytics]]

==History==

Prescriptive analytics incorporates both structured and unstructured data, and uses a combination of advanced analytic techniques and disciplines to predict, prescribe, and adapt. While the term prescriptive analytics was first coined by [[IBM]],<ref name="LustigEtAl:0" /> and was later trademarked[[trademark]]ed by Texas-based company Ayata,<ref>[https://ayata.com/ Ayata], accessed 4 December 2022</ref><ref name=tm>{{Cite web | url=http://trademarks.justia.com/852/06/prescriptive-analytics-85206495.html | title=PRESCRIPTIVE ANALYTICS Trademark - Registration Number 4032907 - Serial Number 85206495 :: Justia Trademarks}}</ref> the underlying concepts have been around for hundreds of years. The technology behind prescriptive analytics synergistically combines hybrid [[data]], business rules with [[mathematical model]]s and [[computational model]]s. The data inputs to prescriptive analytics may come from multiple sources: internal, such as inside a corporation; and external, also known as environmental data. The data may be structured, which includes numbers and categories, as well as [[unstructured data]], such as texts, images, sounds, and videos. Unstructured data differs from [[structured data]] in that its format varies widely and cannot be stored in traditional relational databases without significant effort at data transformation.<ref>{{cite book|last=Inmon|first=Bill|author2=Nesavich, Anthony|title=Tapping Into Unstructured Data|year=2007|publisher=Prentice-Hall|isbn=978-0-13-236029-6}}</ref> More than 80% of the world's data today is unstructured, according to IBM.<ref>{{Cite web |date=2012-03-07 |title=IBM100 - TAKMI: Bringing Order to Unstructured Data |url=http://www-03.ibm.com/ibm/history/ibm100/us/en/icons/takmi/ |archive-url=https://web.archive.org/web/20120403013240/http://www-03.ibm.com/ibm/history/ibm100/us/en/icons/takmi/ |url-status=dead |archive-date=April 3, 2012 |access-date=2023-05-01 |website=www-03.ibm.com |language=en-US}}</ref>

Ayata's trade mark was cancelled in 2018.<ref name=tm />

In addition to this variety of data types and growing data volume, incoming data can also evolve with respect to velocity, that is, more data being generated at a faster or a variable pace. Business rules define the [[business process]] and include objectives constraints, preferences, policies, best practices, and boundaries. Mathematical models and computational models are techniques derived from mathematical sciences, computer science and related disciplines such as applied statistics, machine learning, operations research, natural language processing, computer vision, pattern recognition, image processing, speech recognition, and signal processing. The correct application of all these methods and the verification of their results implies the need for resources on a massive scale including human, computational and temporal for every Prescriptive Analytic project. In order to spare the expense of dozens of people, high performance machines and weeks of work one must consider the reduction of resources and therefore a reduction in the accuracy or reliability of the outcome. The preferable route is a reduction that produces a probabilistic result within acceptable limits.{{fact|date=May 2020}}

==Applications in Oil and Gas==

[[File:Key Questions Prescriptive Analytics software answers for oil and gas producers.png|thumb|right|450px|Key Questions Prescriptive Analytics software answers for oil and gas producers]]Energy is the largest industry in the world ($6 trillion in size). The processes and decisions related to oil and natural gas exploration, development and production generate large amounts of data. Many types of captured data are used to create models and images of the Earth’s structure and layers 5,000 - 35,000 feet below the surface and to describe activities around the wells themselves, such as depositional characteristics, machinery performance, oil flow rates, reservoir temperatures and pressures.<ref>{{cite journal|last= Basu, Atanu|title= How Prescriptive Analytics Can Reshape Fracking in Oil and Gas Fields|journal= Data-Informed|date=November 2012}}</ref> Prescriptive analytics software can help with both locating and producing hydrocarbons<ref>{{cite journal|last= Basu, Atanu |title= How Data Analytics Can Help Frackers Find Oil |journal= Datanami|date=December 2013}}</ref> by taking in seismic data, well log data, production data, and other related data sets to prescribe specific recipes for how and where to drill, complete, and produce wells in order to optimize recovery, minimize cost, and reduce environmental footprint.<ref>{{cite journal|last= Mohan, Daniel |title= Machines Prescribing Recipes from 'Things,' Earth, and People |journal =Oil & Gas Investor|date=August 2014}}</ref>

===Unconventional Resource Development===

[[File:Varied datasets.png|thumb|right|450px|Examples of structured and unstructured data sets generated and by the oil and gas companies and their ecosystem of service providers that can be analyzed together using Prescriptive Analytics software]]With the value of the end product determined by global commodity economics, the basis of competition for operators in upstream E&P is the ability to effectively deploy capital to locate and extract resources more efficiently, effectively, predictably, and safely than their peers. In unconventional resource plays, operational efficiency and effectiveness is diminished by reservoir inconsistencies, and decision-making impaired by high degrees of uncertainty. These challenges manifest themselves in the form of low recovery factors and wide performance variations.

Prescriptive Analytics software can accurately predict production and prescribe optimal configurations of controllable drilling, completion, and production variables by modeling numerous internal and external variables simultaneously, regardless of source, structure, size, or format.<ref>{{cite journal |last=Basu, Mohan, Marshall, & McColpin |title=The Journey to Designer Wells |journal=Oil & Gas Investor |date=December 23, 2014}}</ref> Prescriptive analytics software can also provide decision options and show the impact of each decision option so the operations managers can proactively take appropriate actions, on time, to guarantee future exploration and production performance, and maximize the economic value of assets at every point over the course of their serviceable lifetimes.<ref>{{cite journal |last=Mohan, Daniel |title=Your Data Already Know What You Don't |journal=E&P Magazine |date=September 2014}}</ref>

===Oilfield Equipment Maintenance===

In the realm of oilfield equipment maintenance, Prescriptive Analytics can optimize configuration, anticipate and prevent unplanned downtime, optimize field scheduling, and improve maintenance planning.<ref>{{cite journal |last=Presley, Jennifer |title=ESP for ESPs |journal=Exploration & Production |date=July 1, 2013}}</ref> According to [[General Electric]], there are more than 130,000 electric submersible pumps (ESP's) installed globally, accounting for 60% of the world's oil production.<ref>{{cite web | url=http://www.ge-energy.com/products_and_services/products/electric_submersible_pumping_systems/ | title=Electric Submersible Pumping Systems &#124; GE Energy }}</ref> Prescriptive Analytics has been deployed to predict when and why an ESP will fail, and recommend the necessary actions to prevent the failure.<ref>{{cite journal |last=Wheatley, Malcolm |title=Underground Analytics |journal=DataInformed |date=May 29, 2013}}</ref>

In the area of [[Healthhealth, Safetysafety and Environment|Health, Safety, and Environmentenvironment]], prescriptive analytics can predict and preempt incidents that can lead to reputational and financial loss for oil and gas companies.

In the realm of oilfield equipment maintenance, Prescriptive Analytics can optimize configuration, anticipate and prevent unplanned downtime, optimize field scheduling, and improve maintenance planning.<ref>{{cite journal |last=Presley, Jennifer |title=ESP for ESPs |journal=Exploration & Production |date=July 1, 2013}}</ref> According to General Electric, there are more than 130,000 electric submersible pumps (ESP's) installed globally, accounting for 60% of the world's oil production.<ref>{http://www.ge-energy.com/products_and_services/products/electric_submersible_pumping_systems/}</ref> Prescriptive Analytics has been deployed to predict when and why an ESP will fail, and recommend the necessary actions to prevent the failure.<ref>{{cite journal |last=Wheatley, Malcolm |title=Underground Analytics |journal=DataInformed |date=May 29, 2013}}</ref>

In the area of [[Health, Safety and Environment|Health, Safety, and Environment]], prescriptive analytics can predict and preempt incidents that can lead to reputational and financial loss for oil and gas companies.

===Pricing===

Pricing is another area of focus. [[Natural gas prices]] fluctuate dramatically depending upon supply, demand, [[econometrics]], [[geopolitics]], and weather conditions. Gas producers, pipeline transmission companies and [[Utilityutility companies|utility firms]] have a keen interest in more accurately predicting gas prices so that they can lock in favorable terms while hedging downside risk. Prescriptive analytics software can accurately predict prices by modeling internal and external variables simultaneously and also provide decision options and show the impact of each decision option.<ref>{{cite journal |last1=Watson |first1=Michael |title=Advanced Analytics in Supply Chain - What is it, and is it Better than Non-Advanced Analytics? |journal=SupplyChainDigest |date=November 13, 2012 |url=http://www.scdigest.com/experts/DrWatson_12-11-13.php?cid=6421 }}</ref>

==Applications in maritime industry ==

Pricing is another area of focus. [[Natural gas prices]] fluctuate dramatically depending upon supply, demand, [[econometrics]], [[geopolitics]], and weather conditions. Gas producers, pipeline transmission companies and [[Utility companies|utility firms]] have a keen interest in more accurately predicting gas prices so that they can lock in favorable terms while hedging downside risk. Prescriptive analytics software can accurately predict prices by modeling internal and external variables simultaneously and also provide decision options and show the impact of each decision option.<ref>{{cite journal |last1=Watson |first1=Michael |title=Advanced Analytics in Supply Chain - What is it, and is it Better than Non-Advanced Analytics? |journal=SupplyChainDigest |date=November 13, 2012 |url=http://www.scdigest.com/experts/DrWatson_12-11-13.php?cid=6421 }}</ref>

Common Structural Rules for  Bulk Carriers and Oil Tankers ( [https://iacs.org.uk/publications/common-structural-rules/ managed by IACS organisation] ) intensively utilizes the term "'''prescriptive requirements'''"  as one of two main classes of checkable calculations by dedicated numerical tools and algorithms for verifying safety of ship hull construction.

==Applications in healthcare==

Multiple factors are driving [[healthcare]] providers to dramatically improve business processes and operations as the [[Health care in the United States|United States healthcare]] industry embarks on the necessary migration from a largely fee-for service, volume-based system to a fee-for-performance, value-based system. Prescriptive analytics is playing a key role to help improve the performance in a number of areas involving various stakeholders: payers, providers and pharmaceutical companies.

Prescriptive analytics can help providers improve effectiveness of their clinical care delivery to the population they manage and in the process achieve better patient satisfaction and retention. Providers can do better population health management by identifying appropriate intervention models for risk stratified population combining data from the in-facility care episodes and home based telehealth.<!-- It's unclear how the definition of prescriptive analytics providesprovided distinguishes itself from the well established area of EBM (evidence based medicine) -->

Multiple factors are driving [[healthcare]] providers to dramatically improve business processes and operations as the [[Health care in the United States|United States healthcare]] industry embarks on the necessary migration from a largely fee-for service, volume-based system to a fee-for-performance, value-based system. Prescriptive analytics is playing a key role to help improve the performance in a number of areas involving various stakeholders: payers, providers and pharmaceutical companies.

Prescriptive analytics can help providers improve effectiveness of their clinical care delivery to the population they manage and in the process achieve better patient satisfaction and retention. Providers can do better population health management by identifying appropriate intervention models for risk stratified population combining data from the in-facility care episodes and home based telehealth.<!-- It's unclear how the definition of prescriptive analytics provides distinguishes itself from the well established area of EBM (evidence based medicine) -->

Prescriptive analytics can also benefit healthcare providers in their capacity planning by using analytics to leverage operational and usage data combined with data of external factors such as economic data, population demographic trends and population health trends, to more accurately plan for future capital investments such as new facilities and equipment utilization as well as understand the trade-offs between adding additional beds and expanding an existing facility versus building a new one.<ref>{{cite journal|last=Foster, Roger|title=Big data and public health, part 2: Reducing Unwarranted Services|journal=Government Health IT|date=May 2012}}</ref>

Prescriptive analytics can help pharmaceutical companies to expedite their drug development by identifying patient cohorts that are most suitable for the clinical trials worldwide - patients who are expected to be compliant and will not drop out of the trial due to complications. Analytics can tell companies how much time and money they can save if they choose one patient cohort in a specific country vs. another.

In provider-payer negotiations, [[Health care provider|providers]] can improve their negotiating position with health insurers by developing a robust understanding of future service utilization. By accurately predicting utilization, providers can also better allocate personnel.

==See also==

{{div col|colwidth=22em}}

{{Col-begin}}

{{Col-1-of-2}}

* [[Analytics]]

* [[Applied statistics|Applied Statistics]]

Line 56 ⟶ 64:

* [[Data mining]]

* [[Decision Management]]

{{Col-2-of-2}}

* [[Decision Engineering]]

* [[Forecasting]]

Line 64 ⟶ 71:

* [[Operations research|Operations Research]]

* [[Statistics]]

{{div col- end}}

==Notes==

{{notelist}}

==References==

{{reflist|2}}

{{refbegin}}

==Further reading==

{{refbegin|30em}}

* [[Thomas H. Davenport|Davenport, Thomas H.]]., Kalakota, Ravi, Taylor, James, Lampa, Mike, Franks, Bill, Jeremy, Shapiro, Cokins, Gary, Way, Robin, King, Joy, Schafer, Lori, Renfrow, Cyndy and Sittig, Dean, [https://web.archive.org/web/20120131154904/http://iianalytics.com/wp-content/uploads/2011/12/2012-IIA-Predictions-Brief-Final.pdf ''Predictions for Analytics in 2012''] International Institute for Analytics (December 15, 2011)

* Bertolucci, Jeff, [http://www.informationweek.com/big-data/news/big-data-analytics/prescriptive-analytics-and-big-data-nex/240152863 ''Prescriptive Analytics and Data: Next Big Thing?''] InformationWeek. (April 15, 2013).

* Basu, Atanu, [http://www.analytics-magazine.org/march-april-2013/755-executive-edge-five-pillars-of-prescriptive-analytics-success ''Five Pillars of Prescriptive Analytics Success''] Analytics. (March / April 2013).

* Laney, Douglas and Kart, Lisa, (March 20, 2012). [http://www.parabal.com/uploads/docs/Greenplum/Emerging%20Role%20of%20the%20Data%20Scientist%20and%20the%20Art%20of%20Data%20Science.pdf ''Emerging Role of the Data Scientist and the Art of Data Science''] [[Gartner]].

* [[Robert R. McCormick School of Engineering and Applied Science|McCormick Northwestern Engineering]] [http://www.analytics.northwestern.edu/analytics-examples/prescriptive-analytics.html ''Prescriptive analytics is about enabling smart decisions based on data''].

Line 90 ⟶ 98:

* Wheatley, Malcolm [http://data-informed.com/underground-analytics-the-value-in-predicting-when-an-oil-pump-fails/ "Underground Analytics- The Value of Predicting When an Oil Pump Fails"] DataInformed, May 29, 2013.

* Presley, Jennifer [http://www.epmag.com/item/ESP-ESPs_118057 "ESP for ESPs] Exploration & Production Magazine, July 1, 2013

* Basu, Atanu, [http://data-informed.com/prescriptive-analytics-can-reshape-fracking-oil-gas-fields/ "How Prescriptive Analytics Can Reshape Fracking in Oil & Gas"], DataInformed, December 10, 2013.

* Basu, Atanu [https://www.wired.com/insights/2014/01/big-data-analytics-can-deliver-u-s-energy-independence/ "What The Frack: U.S. Energy Prowess with Shale, Big Data Analytics"] WIRED Blog. (January 2014).

* Logan, Amy [http://www.ugcenter.com/Technology/Science-Fiction-A-Fact-The-EP-World_134336/ "Science Fiction Now a Fact in the E&P World"] Unconventional Oil & Gas Center, June 2, 2014.

* Mohan, Daniel [http://www.epmag.com/item/Your-data-know-you-dont_137311/ "Your Data Already Know What You Don't"] Exploration & Production Magazine, September, 2014.

* van Rijmenam, Mark [https://datafloq.com/read/future-big-data-use-cases-prescriptive-analytics/668"The Future of Big Data? Three Use Cases of Prescriptive Analytics"] Datafloq, December 29, 2014.

* {{cite journal |last1=Lepenioti |first1=Katerina |last2=Bousdekis |first2=Alexandros |last3=Apostolou |first3=Dimitris |last4=Mentzas |first4=Gregoris |title=Prescriptive analytics: Literature review and research challenges |journal=International Journal of Information Management |date=1 February 2020 |volume=50 |pages=57–70 |doi=10.1016/j.ijinfomgt.2019.04.003 }}

{{refend}}

==External links==

<!-- Do not add forum, reseller, spam links to this article -->

* [httphttps://analyticsmagazinepubsonline.cominforms.org/magazine/analytics INFORMS' bi-monthly, digital magazine on the analytics profession]

* Menon, Jai [https://www.youtube.com/watch?v=VtETirgVn9c "Why Data Matters: Moving Beyond Prediction"] IBM

* [https://www.gopeaks.org/ Global Openlabs for Performance-Enhancement Analytics and Knowledge System (GoPeaks)]

[[Category:Types of analytics]]

[[Category:Big data|analytics]]

[[Category:Business intelligence terms]]

[[Category:Business terms]]

[[Category:Formal sciences]]

[[Category:Health care]]