big data - ftpi

35
1 Big Data in Action ปริญญ์ เสรีพงศ์ สถาบันเพิ ่มผลผลิตแห ่งชาติ

Upload: others

Post on 08-Jan-2022

1 views

Category:

Documents


0 download

TRANSCRIPT

1

Big Data in Action

ปริญญ์ เสรีพงศ์ สถาบนัเพิ่มผลผลิตแห่งชาต ิ

2 2

Enterprise Analytics

Customers Analytics

Competitors Analytics

Strategic Insight in Three Domains

Competitive Advantage 1 2 3

3 3

Environmental

Scanning (In & Ex)

Strategy

Formulation Strategy

Implementation Evaluation and Control

Gathering Information

Long-range Plans

Putting Strategy into Action

Monitoring Performance

Big Data in Strategic Management

Credit : Strategic Management and Business Policy, 14th edition by Thomas L. Wheelen

Data-driven through analytic

4

External Scanning

PEST

Analysis

Economic

Social

Technology

Politic

5

Strategic Intelligence External Scanning

Dr. Santhi Kanktanaporn

5

6

Analytic

Insights for Decision Making

Strategic Intelligence External Scanning

Dr. Santhi Kanktanaporn

6

7

Poter’s Value Chain Internal Scanning

8 8

Big Data In

Performance Excellence Framework

9

Malcolm Baldrige National Quality Award

Thailand Quality Award

Criteria for Performance Excellence

10

Strategic Insight and Big Data

11

“องค์กรต้องจัดการกับการวิเคราะห์ข้อมูลที่ซับซ้อนมากขึ้น รวมถึงประเด็นความถูกต้องเชื่อถือได้ของข้อมูลความท้าทายในด้านการรักษาความปลอดภัยบนไซเบอร”์

เกณฑ์รางวัลคุณภาพแห่งชาติ ปี 2559-2560

12

13

Big Data Analytic Real Cases

14

THE PANANA PAPERS Power of Text Analytics

15

Power of Text Analytics

Gathering information | Full text search | Graph Database

16

17

Analyzing the Panama Papers with Neo4j

https://neo4j.com/blog/analyzing-panama-papers-neo4j/

18

https://neo4j.com/blog/analyzing-panama-papers-neo4j/

Analyzing the Panama Papers with Neo4j

19

https://www.meconomics.net/content/1143

Power of Text Analytics

20

Food Inspection Forecasting

Power of Predictive analytics

21

Big Data Analytic in Food Inspection Forecasting

https://chicago.github.io/food-inspections-evaluation/

22

“Forecast food establishments that are most likely to have critical violations so that they may be inspected first”

Goal of the Project

23

http://www.foodbornechicago.org/

Report Incident

24

• 15,000 food establishments across the City of Chicago

• Three dozen inspectors from Department of Public Health

• Inspectors responsible nearly 470 food establishments

About Food Inspection

• 100,000 sanitation inspections records • 311 complaints database • Weather database

Data Sources

25

• Establishments that had previous critical or serious violations

• Three-day average high temperature • Nearby garbage and sanitation complaints • The type of facility being inspected • Whether the establishment has a tobacco license or

has an incidental alcohol consumption license • Length of time since last inspection • The length of time the establishment has been

operating • Inspector assigned

Predictors of food inspection outcomes

26

Department of Public Health

Civic Consulting

Alliance

Allstate Insurance Company

Power of Collaboration

27

Before After Perc

enta

ge

Result : Percentage of critical violations

Business-as-usual Data-driven

56%

69%

28

Human Resource Analytic

Power of Exploratory Analytics

Why Employees leave ??

29

1. Satisfaction Level 2. Last evaluation 3. Number of projects 4. Average monthly hours 5. Time spent at the company 6. Whether they have had a work accident 7. Whether they have had a promotion in the

last 5 years 8. Departments (column sales) 9. Salary 10. Whether the employee has left

Human Resource Analytics

10 Features :

Data set 14,999 rows

30 Cr : yassineghouzam

Data Exploratory Analytics

Department Salary

Low Medium High

31

Satisfaction

Left

Correlation between features

Cr : yassineghouzam

32

Cr : yassineghouzam

Data Exploratory Analytics

33

Sati

sfac

tio

n L

evel

Left Satisfaction Level

Stay

Left

Data Exploratory Analytics

34

Clusters of Leaf Employees

Satisfaction Level

Last

Eva

luat

ion

35

Stay Left Success-Unhappy Left Success-Happy Left Unsuccess-Unhappy

Number of Project

Last Evaluation

Avg monthly hrs

Time spent at the company

Satisfaction Level

Radar chart : stayed and Left employees