Post Graduate Diploma in Supply
Post Graduate Diploma in Supply
Chain Management (SCM)
Chain Management (SCM)
FUNDAMENTALS OF
Course Name: Supply Chain Analytics (SCA)
Course Name: Supply Chain Analytics (SCA)
Module – 1
Data And Statistics
Copyright © Institute of Industrial Learning 2
LEARNING OBJECTIVES
⮚ Understand the fundamental concepts of descriptive statistics.
⮚ Grasp the concept of probability distributions and their significance in statistical analysis.
⮚ Comprehend the characteristics and applications of the normal distribution.
⮚ Understand the Poisson distribution and its application to model random events.
⮚ Learn the concept of confidence intervals and their role in statistical estimation.
⮚ Explore the use of prediction intervals and understand the basics of regression analysis.
⮚ Apply statistical concepts to solve practical problems in various fields.
⮚ Develop critical thinking skills in the application of statistical methods.
⮚ Enhance communication skills in presenting statistical findings.
⮚ Understand the ethical considerations in statistical analysis and reporting.
Copyright © Institute of Industrial Learning 3
WHAT IS SUPPLY CHAIN ANALYTICS?
Supply chain analytics is the process of identifying known risks and help to predict future risks
by spotting patterns and trends throughout the supply chain.
HOW DOES SUPPLY CHAIN ANALYTICS WORK?
Analytics represent the ability to make data-driven decisions, based on a summary of relevant,
trusted data, often using visualization in the form of graphs, charts and other means. Supply
chains typically generate massive amounts of data. Supply chain analytics helps to make sense
of all this data — uncovering patterns and generating insights.
Copyright © Institute of Industrial Learning 4
WHAT ARE THE TYPES OF SUPPLY CHAIN ANALYTICS?
1) Descriptive analytics-
Provides visibility and a single source of truth across the supply chain, for both internal and external
systems and data.
2) Predictive analytics-
Helps an organization understand the most likely outcome or future scenario and its business
implications. For example, by using predictive analytics, you can project and mitigate disruptions and
risks.
3) Prescriptive analytics-
Helps organizations solve problems and collaborate for maximum business value. Helps businesses
collaborate with logistic partners to reduce time and effort in mitigating disruptions.
4) Cognitive analytics-
Helps an organization answer complex questions in natural language — in the way a person or team
of people might respond to a question. It assists companies to think through a complex problem or
issue, such as “How might we improve or optimize X?”
Copyright © Institute of Industrial Learning 5
KEY FEATURES OF EFFECTIVE SUPPLY CHAIN ANALYTICS
❖ Connected: Being able to access unstructured data from social media, structured data from the
Internet of Things (IoT) and more traditional data sets available through traditional ERP and B2B
integration tools.
❖ Collaborative: Improving collaboration with suppliers increasingly means the use of cloud-based
commerce networks to enable multi-enterprise collaboration and engagement.
❖ Cyber-aware: The supply chain must harden its systems from cyber-intrusions and hacks, which
should be an enterprise-wide concern.
❖ Cognitively enabled: The AI platform becomes the modern supply chain’s control tower by
collating, coordinating and conducting decisions and actions across the chain. Most of the supply
chain is automated and self-learning.
❖ Comprehensive: Analytics capabilities must be scaled with data in real time. Insights will be
comprehensive and fast. Latency is unacceptable in the supply chain of the future.
Copyright © Institute of Industrial Learning 6
CHARACTERIZING A DISTRIBUTION
Several ways to characterize a distribution:
❑ Central Tendency – what is the “most likely” value?
❑ Spread – how much do the observations “differ”?
Copyright © Institute of Industrial Learning 7
CENTRAL TENDENCY METRICS
Copyright © Institute of Industrial Learning 8
CENTRAL TENDENCY- MEAN
Copyright © Institute of Industrial Learning 9
SPREAD METRICS
Copyright © Institute of Industrial Learning 10
SPREAD- VARIANCE
Copyright © Institute of Industrial Learning 11
SUMMARY STATISTICS
Copyright © Institute of Industrial Learning 12
PROBABILITY DISTRIBUTIONS
Copyright © Institute of Industrial Learning 13
DISCRETE THEORETICAL DISTRIBUTIONS
Copyright © Institute of Industrial Learning 14
POISSON DISTRIBUTION
Copyright © Institute of Industrial Learning 15
POISSON DISTRIBUTION – FOR DIFFERENT Λ VALUES
Copyright © Institute of Industrial Learning 16
POISSON DISTRIBUTION
Copyright © Institute of Industrial Learning 17
SUMMARY STATISTICS FOR SPREADSHEETS
Copyright © Institute of Industrial Learning 18
WEEKLY TASK1- SUNNY CRACKERS DCS
Copyright © Institute of Industrial Learning 19
SUNNY CRACKERS DC-EAST: WEEKLY DEMAND
Copyright © Institute of Industrial Learning 20
CONTINUOUS PROBABILITY DISTRIBUTIONS
Copyright © Institute of Industrial Learning 21
NORMAL DISTRIBUTION
Copyright © Institute of Industrial Learning 22
UNIT OR STANDARD NORMAL DISTRIBUTION
Copyright © Institute of Industrial Learning 23
NORMAL FUNCTIONS FOR SPREADSHEETS
Copyright © Institute of Industrial Learning 24
SUNNY CRACKERS TRANSPORTATION
Copyright © Institute of Industrial Learning 25
DUFFY INDUSTRIES
Copyright © Institute of Industrial Learning 26
DUFFY INDUSTRIES
Copyright © Institute of Industrial Learning 27
DEPENDENT VS. INDEPENDENT VARIABLES
Copyright © Institute of Industrial Learning 28
LINEAR REGRESSION MODEL
Copyright © Institute of Industrial Learning 29
VALIDATING A MODEL – FIRST STEPS
MODEL EVALUATION METRICS
Copyright © Institute of Industrial Learning 30
MODEL 1: CPL = B0 + B1(DIST)
Copyright © Institute of Industrial Learning 31
Copyright © Institute of Industrial Learning 32
Copyright © Institute of Industrial Learning 33
HOW CAN WE IMPROVE THE MODEL?
Copyright © Institute of Industrial Learning 34
MODEL 2: CPL = B0 + B1(DIST) + B2(WGT)
Copyright © Institute of Industrial Learning 35
MODELING CATEGORICAL VARIABLES
Copyright © Institute of Industrial Learning 36
MODEL 3: CPL = B0 + B1(DIST) + B2(REFFLAG)
Copyright © Institute of Industrial Learning 37
Copyright © Institute of Industrial Learning 38
Copyright © Institute of Industrial Learning 39
MODULE 1 TASKS-
TASK1-
OPEN THE FILE “MODULE1_TASK1_SUNNY CRACKERSDC_DATA.XLSX” FILE AND FILL IN THE GREEN
CELLS AND SUBMIT.
TASK2-
OPEN THE FILE “MODULE1_TASK2_DUFFYINDUSTRIES_DATA.XLSX” AND BUILD REGRESSION MODEL
2 AND 3 AS PER SLIDE.
Copyright © Institute of Industrial Learning 40
LEARNING OUTCOMES
⮚ Describe and summarize data using appropriate measures of central tendency and dispersion.
⮚ Differentiate between discrete and continuous probability distributions and apply them to solve
real-world problems.
⮚ Apply the properties of the normal distribution to analyze data and make statistical inferences.
⮚ Application of the Poisson distribution to solve problems involving the occurrence of rare events.
⮚ Construct and interpret confidence intervals for population parameters.
⮚ Perform simple regression analysis, interpret regression coefficients, and construct prediction
intervals for individual observations.
⮚ Critically evaluate data, identify appropriate statistical techniques, and solve problems in diverse
contexts.
⮚ Effectively communicate statistical results, conclusions, and interpretations to diverse audiences.
Copyright© Institute of Industrial Learning 41
Any
Copyright © Institute of Industrial Learning 42
Thank You
Copyright © Institute of Industrial Learning 43