Scribd
Upload
8 views13 pages

Topic Guess ???: Indian

Uploaded by

subha20031104
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views13 pages

Topic Guess ???: Indian

Uploaded by

subha20031104
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

SNS College of Technology

Coimbatore - 35

19BAZ782 – Analytics for Everyone

Unit IV – Predictive Analytics I

Topic…Guess…???
1 Indian
st

Presented by Institution Design


Thinking
to
Implement Curriculum
Ms. Viveka T Redesigning Common Mind and Business
Design Thinker Towards Excellence
Recall

• Forecasting
• Additive Model
• Multiplicative Model
• Time series technique
• Errors in regression

2 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Guess the topic…???

3 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Smoothing in Analytics

4 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Concept

• 1950s – One of the


successful model
• Works on weight model
• Suitable for no clear
trend or seasonal
pattern
• Types: Single, Double
and Triple
5 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Concept…
• Single Exponential Smoothing
• Alpha [Smoothing Factor or Smoothing
Coefficient]
• Alpha: 0 to 1 [Past data – Recent data]
• Double Exponential Smoothing
• Extended Version – Influenced by Trend
• Alpha & Beta [Additional Smoothing factor]
• Additive Trend: Double Exponential Smoothing
with a linear trend
• Multiplicative Trend: Double Exponential
Smoothing with an exponential trend

6 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Concept…

• Triple Exponential Smoothing


• Seasonality
• Also called as Hot Winter Exponential
Smoothing
• Gamma: Influence of Seasonal
component
• Additive Trend: Triple Exponential
Smoothing with a linear trend
• Multiplicative Trend: Triple Exponential
Smoothing with an exponential trend

7 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Single ES

Ft+1 = Ft + a(At - Ft) Need initial


forecast Ft
Ft+1 = Forecast value for time t+1 to start.

At = Actual value at time t


ά = Smoothing constant

8 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Example
Week Demand
Given the weekly demand
1 820
2 775 data what are the exponential
3 680 smoothing forecasts for
4
5
655
750
periods 2-10 using a=0.10?
6 802
7 798 Assume F1=D1
8 689
9 775
10
9 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Solution
Ft+1 = Ft + a(At - Ft)
Week Demand 0.1 0.6
1 820 820.00 820.00 =820+.1(820–820)
2 775 820.00 820.00 =820
3 680 815.50 793.00
4 655 801.95 725.20
5 750 787.26 683.08
6 802 783.53 723.23
7 798 785.38 770.49
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28

10 / 12
Summary

• Exponential Smoothing
• Concepts and its types
• Problem on Single
Exponential Smoothing

11 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Reference

• https://machinelearningmastery.com/exponential-
smoothing-for-time-series-forecasting-in-python/
• https://www.statisticshowto.com/exponential-smoothing/

12 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I
Reach Us
snsinstitutions

snsinstitutions

snsinstitutions

snsinstitutions

snsinstitutions
13 / 12
26.06.2024 Ms.Viveka, AP/MBA/SNSCT – Predictive Analytics I

You might also like