Professional Documents
Culture Documents
Understanding Forecasting
Analytics in Forecasting
Forecasting Techniques
Modern day forecasting Challenges
• One of the biggest challenges for business executives today is demand volatility in
relation to demand forecasting.
• Whereas data availability continues to increase, customer purchase patterns are
becoming increasingly complex
• That makes prediction harder
• There are too many factors influencing demand, ranging from weather fluctuations
to posts by social media influencers, causing customers to frequently changing
their minds.
• things that will reshape customer intentions will mostly happen quite
unexpectedly. Traditional Forecasts are only as accurate as the data, models,
resources and people that have to interpret them.
• how can we respond to these challenges?
AI and ML a solution ??
Are AI and machine learning the future for demand forecasting?
Demand forecasting is at the heart of every retailer’s supply chain, and for good
reason: the demand forecast is central to sales, profitability and the customer
shopping experience, and it has a ripple effect throughout the supply chain.
Yet despite a wealth of established demand forecasting solutions and
methodologies, retailers struggle to produce accurate, timely demand forecasts.
Danone uses many promotions and media events. More than 30% of
the total volume is sold through promotional offers such as discounts
and leaflets, so the demand forecasts were somewhat ad hoc
‘RIGHT DATA’ ANALYTICS WILL SURPASS BIG DATA ANALYTICS AS A KEY TREND
• Current reality is not knowing what sales will be, purchase new equipment despite
uncertainty about demand for products, and make investments without knowing what
profits will be.
• Managers are always trying to make better estimates of what will happen in the future
in the face of uncertainty.
• Making good estimates is the main purpose of FORECASTING
Demand Forecasting
https://www.youtube.com/watch?v=HQ7C
I7JlXJQ
Forecasting Challenges
Data Normalization
Year Sales Quantity Year Sales Quantity
2000 28 2000 28
2001 33 2001 33
2002 37 2002 37
2003 39 2003 39
2004 40 2004 40
2005 38 2005 38
2006 41 2006 41
2007 42 2007 42
2008 47 2008 47
2009 41 2009 41
2010 92 2010 42
2011 51 2011 51
2012 50 2012 50
2013 48 2013 48
2014 54 2014 54
2015 56 2015 56
2016 61 2016 61
2017 64 2017 64
2018 66 2018 66
2019 71 2019 71
Data Normalization
Year Sales Quantity Year Sales Quantity
2000 28 2000 28
2001 33 2001 33
2002 37 2002 37
2003 39 2003 39
2004 40 2004 40
2005 38 2005 38
2006 2006 38
2007 2007 40
2008 2008 42
2009 2009 44
2010 2010 46
2011 2011 48
2012 2012 50
2013 2013 52
2014 54 2014 54
2015 56 2015 56
2016 2016 59
2017 2017 62
2018 66 2018 66
2019 71 2019 71
Man Machine Collaboration
Month 2017 2018 2019 2020
Jan 0 0 0 0
Feb 0 0 0 0
Mar 0 0 0 0
Apr 0 0 0 0
May 0 0 0 0
Jun 0 0 0 0
Jul 0 0 0 0
Aug 0 0 0 ?
Sep 0 0 0 ?
Oct 0 0 0 ?
Nov 0 0 0 ?
Dec 1 1 1 ?
Panel Discussion 1
Only customer who were buying is likely to
change technology?
Sales annually for this unit is $1Million
What will be your forecast?
Man Machine Collaboration
Month 2017 2018 2019 2020
Jan 0 0 0 0
Feb 0 0 0 0
Mar 0 0 0 0
Apr 0 0 0 0
May 0 0 0 0
Jun 0 0 0 0
Jul 0 0 0 0
Aug 0 0 0 ?
Sep 0 0 0 ?
Oct 0 0 0 ?
Nov 0 0 0 ?
Dec 1 1 1 ?
Panel Discussion 2
Customer has changed technology
There are other customers in the market
What will be your forecast?
AI Plus Human Intelligence
• However, no matter how smart the forecasting solution may be,
Human logic is still needed to evaluate the relevance of the
outcomes produced by AI solutions.
Delphi method
A forecasting technique using a group process that allows experts to make
forecasts.
Market survey
A forecasting method that solicits input from customers or potential
customers regarding future purchasing plans
Quantitative Methods
Quantitative Methods
Naive approach
A forecasting technique that assumes that demand in the next period is equal
to demand in the most recent period.
Moving averages
A forecasting method that uses an average of the n most recent periods of
data to forecast the next period.
Exponential smoothing
A weighted-moving-average forecasting technique in which data points are
weighted by an exponential function
Quantitative Methods
Trend projection
A time-series forecasting method that fits a trend line to a series of historical
data points and then projects the line into the future for forecasts
Linear-regression analysis
A straight-line mathematical model to describe the functional relationships
between independent and dependent variables