Scribd
Upload
30 views

Predictive Analytics in Operations

Predictive analytics uses historical data and statistical techniques to predict future events and trends. There are three main types of predictive models: predictive models, which analyze relationships between input data attributes; descriptive models, which classify customers and products into groups; and decision models, which predict decisions involving multiple variables. Common predictive analytics techniques used in operations include regression, correlation, and machine learning to optimize processes, forecast demand, reduce costs and waste, and improve quality.

Uploaded by

yaswanth
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
30 views

Predictive Analytics in Operations

Predictive analytics uses historical data and statistical techniques to predict future events and trends. There are three main types of predictive models: predictive models, which analyze relationships between input data attributes; descriptive models, which classify customers and products into groups; and decision models, which predict decisions involving multiple variables. Common predictive analytics techniques used in operations include regression, correlation, and machine learning to optimize processes, forecast demand, reduce costs and waste, and improve quality.

Uploaded by

yaswanth
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

PREDICTIVE

A N A LY T I C S I N
O P E R AT I O N S
PREDICTIVE ANALYTICS
• Predictive analytics is the branch of the advanced analytics uses historical data to predict
future events.
• Predictive analytics uses many techniques from data mining, statistics, modeling, machine
learning, and artificial intelligence to analyze current data to make predictions about future.
TYPES:
• Predictive Model:
 Predictive model analyze the relationship between one or more attributes of input data.
 These models are used to estimate the likelihood that a similar unit that exhibit the same
performance in different places.
 This category focuses on modelling in many fields such as operations management where they
understand the complex data patterns revealing customer performance & identifying the
fraudulent activities in a business.
 Predictive model perform calculation over live transaction in order to solve many issues to
operational management such as to evaluate the risk of the business.
• Descriptive Model:
 Descriptive models used to establish the relationship in data which is used to classify customers and
products into groups.
 Descriptive modelling differs from predictive modelling in a way that it identifies many different
relationship between customers and products.
 Descriptive model differs from predictive analysis in a way that as they do not rank the customers on the
basis of their behavior to a particular action.
 Descriptive model are used to classify the customers based on their product selection.

• Decision Model:
 Decision model establish the relationship between all the elements of decision, (the known data
attributes, the decisions, the results forecasted..), in order to predict decision that involves in several
variables.
 These models are used in optimizing the favorable outcomes i.e maximizing the interest ones and
minimizing the uninterested ones.
 Decision models are used to produce set of logical decisions and business rules that will considered
every action of customers.
3 KINDS OF PREDICTION TECHNICS
USED FOR OPERATIONS:

• Judgmental Forecasts:
 This forecasting technique make prediction on subjective inputs from various sources.
 This type of forecasting technique used when the data is outdated or if there is short time to collect the data
 Judgmental Forecasting has several types of surveys such as customer surveys, sales force opinions etc.

• Time series Forecast:


 Time series forecast is a series of observation that are made at regular interval of time and the sequence is
ordered according to time.
 It uncovers the pattern that are hidden in these observations
 Time series forecast works on quantitative level of prediction and helps predict the future events.
• Associate Model:
 Associative model deals with quantitative prediction in business organization eg: It can be used
for predicting demand or estimating price of a product.
 It includes predictive variables and develops a mathematical equation that predicts value of the
predicting variable.
ANALYTICAL TECHNIQUES
• Predictive analytical Techniques and approaches can be categorized into:
Regression Technique :
 This technique derive a mathematical equation. The equation derived can be used as a model to
represent the relationship between all the features and attributes under contribution.
 Regression is a statistical measurement to determine the strength of the relationship between one
dependent variable (usually denoted by Y) and a series of other changing variables (known as independent
variables).
 Used to measure the cost of process
 Used to estimate the future demand of product
 Used to measure the quality of the product
 To reduce the wastage.

• Regression Model can be further categorized some of them are:


 Linear Regression Model.
 Logistic Linear regression Model.
Correlation Technique:
• Correlation is usually defined as a measure of the linear relationship between two
quantitative variable.
• There are 3 types of correlation
• Positive
• Negative
• Zero
Application Of Correlation In Operations:
 Used to measure the length, weight of the product.
 Control the production process based on previous reports
 Used to measure amount of electricity Vs bill
 Used to measure work vs productivity
 Used to measure quantity of product vs price.
Machine Learning Technique:
 Machine Learning comes under in the field of Artificial Intelligence. It helps computers to learn
and understand.
 It consist of several techniques which find in variety of fields such as fraud deduction, Medical
diagnosis, Analysis of stock market and Weather forecasting etc.
 It is also used to predict the value of unknown dependent variable without analyzing the
relationship between known and independent variables.
 Machine learning technique is used in complex situations to deduce the variables.
• Machine learning technique can be further categorized some of them are:
 Back Propagation Network.
 Support vector Machine etc..
APPLICATIONS OF PREDICTIVE ANALYTICS
• CUSTOMER RELATIONSHIP MANAGEMENT:
 Predictive analytics applications are used to achieve CRM objectives such as marketing
campaigns, sales and customer services. Analytical customer relationship can be applied
through out the customer life cycle, right from acquisition, relationship growth, retention and
win back.

• HEALTH CARE:
 In health care predictive analysis can be determine the patient who are at risk of developing
certain conditions such as diabetes, Asthma and other life time illness. The clinical decision
support systems incorporate predictive analytics to support medical decision making at the
point of care.
• CROSS SELL
 Predictive Analytics application analyses the customer spending usage and other behavior, leading to
efficient cross sales, or selling additional products to current customers for an organization that
offers multiple products

• FRAUD DETECTION
 Predictive analytics application can be find inaccurate credit applications, fraudulent application done
offline and online identify the thefts and false insurance claims.

• RISK MANAGEMENT
 Predictive analytics applications predicts the best portfolio to maximize return in capital assets
pricing model and probabilistic risk assessment to yield accurate forecasts.

• DIRECT MARKETING
 Predictive Analytics can also help to identify the most effective combination of product versions,
marketing material, communication channels and timing that should be used to target a given
customer.

You might also like