Machine Learning Applications

Rishabh Garg
Rishabh GargSoftware Developer en BITS-Pilani | IIT Delhi
Machine Learning Applications
(A Human’s Guide)
RISHABH GARG
BITS - PILANI | GOA
IIT
DELHI
Key technology aspects
CRISP - DM
• CRISP - DM stands for cross-industry standard process for data mining.
• Most widely used and relied upon analytics process in the world (Forbes report).
• Consists of 6 stages:
1. Business understanding
2. Data understanding
3. Data preparation
4. Modeling
5. Evaluation
6. Deployment
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Key technology aspects
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Business Understanding
• First phase of CRISP - DM
• For Data Scientist
1. Key aspect is to understand the business problem and to generate value for the
company.
2. ‘Value is generated by putting models into context within the business processes of a
company to solve problems’.
• For Business Analyst
1. Gap in the understanding of machine learning methods.
Solution : Focus on the mapping of the problem and contemplate for the correct solution.
Traditional methods like Business Intelligence and Six Sigma should be explored before
machine learning.
Key technology aspects
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Defining Labels
• Map the problem into a data science method.
• Supervised learning takes more efforts but is easier to optimize than
unsupervised learning, hence more recommended.
• Unsupervised learning models do not provide a qualitative measure to tune and
evaluate the model.
• Try to convert the supervised learning problem into a targeting problem.
• While selling your business model, try to include lesser equations and
mathematical language in it to be reliable.
Key technology aspects
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Defining Labels
• Answer the questions: ‘What do you want to ask the data?’
Requirements
• Labels need to match the business needs
The problem being worked upon must be aligned with the business goals.
• Labels need to exist
Situations for which very little data is available cannot be used for machine learning model
training.
• Labels need to be actionable
On prediction about the given situation, steps should be taken as per the requirements for
generation of value.
Key technology aspects
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Performance Analysis
• Involves measuring the quality of data science algorithms.
• RMSE, AUC, AUPRC are meant for statistical problems and are less suited to business
problems.
Regression Tasks
• Overestimation and underestimation should be avoided for excess material management
and loss of shipment time respectively.
Classification Tasks
• False positives and false negatives can impact business decisions. Medical tests are a
good example where false positives lead to money loss and false negatives lead to
treatment delay.
Key technology aspects
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Business Aligned Performance
• Value based performance measures can be used i.e, focus on maximizing revenue for the
company rather than good statistical outcomes.
• Such performance measures for unsupervised learning are harder to find.
Defining Success Parameters
• After the project achieves a baseline, deploy and work in parallel.
• Compare our project to the currently deployed models for analysis.
• Else, use the naïve/ simple model approach for performance.
• Use the proper methods pertaining to validation.
Key technology aspects
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Profile Generation
• This primarily involves filtering the data, cleaning the data, scrutiny of sources
and data preparation for accurate results.
• Detection of patterns in data for predicting labels in the machine learning model.
• Establishing time period when the data is available which is different from batch
running processes.
• The raw data is never aggregated in such a way that the aggregated data is as
appropriate for the task of machine learning as the raw data. Thus, to get the
best results possible in your project, it is important to get access to the
underlying data and use that for model training and evaluation.
Business goals
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Automation
• Every business carries some inefficiencies that can be replaced by high
performing algorithms.
Optimization
• Enterprises are using artificial intelligence algorithms to optimize processes that
reduce overheads and improve output.
• Tightening operations means smarter budgeting and more profit.
• AI can autonomously aggregate and crunch data to provide cohesion across
sales and marketing. Data scrapping has been democratized and made
accessible by AI.
Business goals
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
• Data unification and customer
insight are easily and autonomously
accomplished with AI. The business
case for AI rests on its ability to
free-up human time.
• Other technologies such as Smart
Sensors, Microcontrollers, Real
Time Dashboard, Augmented
Reality using Unity etc. can be
integrated to achieve smart
manufacturing.
Roadblocks in Implementation
Questions
What is in it for me ?
Solution: Critically outline the business
problems and define the goals.
That’s not my job ?
Solution: Since 70% projects are not
implemented due to employee resistance
(McKinsey Report). We must, first of all,
clarify the goals and find the people with
leadership qualities to undertake the
project.
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Business Goals for Indian Manufacturers
• Diagnosing problems and taking corrective action in time.
• Enabling entrepreneurs to effectively manage multiple facilities and make them
consumer centric.
• Predictive maintenance and quality analytics.
• Digital twin implementation (a combination of physics modelling Simulink and
real data of a machine).
• Big data driven processes.
• Process visualization and modular production assets.
Elevator Pitch
PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
Indian manufacturing sector typically suffers from downtime, high latency in error
rectification process, and low skilled labour which can be optimized by adopting this
approach.
Downtime can be tackled by predictive maintenance and RUL estimation while error
rectification process can be made faster through suggestions based on real time
data monitoring.
More realization of profits and higher ability to use data are only the bare minimum
benefits that can be received from this. (Power of 1%!!!)
1 de 12

Recomendados

Business analytics por
Business analyticsBusiness analytics
Business analyticsSpringer
699 vistas11 diapositivas
WebXpress Business Intelligence Capability por
WebXpress Business Intelligence CapabilityWebXpress Business Intelligence Capability
WebXpress Business Intelligence CapabilityWebXpress.IN
1.2K vistas41 diapositivas
Making the Business Case for Remote Service Capabilities por
Making the Business Case for Remote Service CapabilitiesMaking the Business Case for Remote Service Capabilities
Making the Business Case for Remote Service CapabilitiesPTC
7.4K vistas20 diapositivas
Rashmi_Das_current por
Rashmi_Das_currentRashmi_Das_current
Rashmi_Das_currentRashmilatha Das
89 vistas4 diapositivas
Case Study: Loan default prediction por
Case Study: Loan default predictionCase Study: Loan default prediction
Case Study: Loan default predictionALTEN Calsoft Labs
4.8K vistas25 diapositivas
Parallel testing overview por
Parallel testing overviewParallel testing overview
Parallel testing overviewBarbara Getter
8.3K vistas30 diapositivas

Más contenido relacionado

La actualidad más candente

Automated legacy portfolio assessment por
Automated legacy portfolio assessmentAutomated legacy portfolio assessment
Automated legacy portfolio assessmentRavikumar Kaliyaperumal
127 vistas9 diapositivas
Application Portfolio Management, the Basics - How much Software do I have por
Application Portfolio Management, the Basics - How much Software do I haveApplication Portfolio Management, the Basics - How much Software do I have
Application Portfolio Management, the Basics - How much Software do I haveFrank Vogelezang
2.8K vistas20 diapositivas
Oracle Enterprise Performance Management por
Oracle Enterprise Performance ManagementOracle Enterprise Performance Management
Oracle Enterprise Performance ManagementBAINIDA
861 vistas16 diapositivas
Nesma autumn conference - Contracting & Performance management - Cees Kuijpers por
Nesma autumn conference - Contracting & Performance management - Cees KuijpersNesma autumn conference - Contracting & Performance management - Cees Kuijpers
Nesma autumn conference - Contracting & Performance management - Cees KuijpersNesma
171 vistas20 diapositivas
CA PPM Rationalizaiton por
CA PPM RationalizaitonCA PPM Rationalizaiton
CA PPM RationalizaitonDavid Messineo
839 vistas13 diapositivas
“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul... por
“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul...“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul...
“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul...VisionID
1.6K vistas28 diapositivas

La actualidad más candente(20)

Application Portfolio Management, the Basics - How much Software do I have por Frank Vogelezang
Application Portfolio Management, the Basics - How much Software do I haveApplication Portfolio Management, the Basics - How much Software do I have
Application Portfolio Management, the Basics - How much Software do I have
Frank Vogelezang2.8K vistas
Oracle Enterprise Performance Management por BAINIDA
Oracle Enterprise Performance ManagementOracle Enterprise Performance Management
Oracle Enterprise Performance Management
BAINIDA861 vistas
Nesma autumn conference - Contracting & Performance management - Cees Kuijpers por Nesma
Nesma autumn conference - Contracting & Performance management - Cees KuijpersNesma autumn conference - Contracting & Performance management - Cees Kuijpers
Nesma autumn conference - Contracting & Performance management - Cees Kuijpers
Nesma171 vistas
“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul... por VisionID
“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul...“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul...
“Unlock Your Manufacturing Data to Drive Manufacturing Optimisation and Resul...
VisionID1.6K vistas
Application Portfolio Assessment Tool por Skip Roncal
Application Portfolio Assessment ToolApplication Portfolio Assessment Tool
Application Portfolio Assessment Tool
Skip Roncal2.1K vistas
Simplifying it using a disciplined portfolio governance approach por p6academy
Simplifying it using a disciplined portfolio governance approachSimplifying it using a disciplined portfolio governance approach
Simplifying it using a disciplined portfolio governance approach
p6academy1.4K vistas
Fusion hcm-presentation-final version por Feras Ahmad
Fusion hcm-presentation-final versionFusion hcm-presentation-final version
Fusion hcm-presentation-final version
Feras Ahmad1.3K vistas
Transforming Business Intelligence Testing por Method360
Transforming Business Intelligence TestingTransforming Business Intelligence Testing
Transforming Business Intelligence Testing
Method3603.2K vistas
Webinar Presentation: Microsoft Dynamics 2013 Year End Close por Emtec Inc.
Webinar Presentation: Microsoft Dynamics 2013 Year End Close Webinar Presentation: Microsoft Dynamics 2013 Year End Close
Webinar Presentation: Microsoft Dynamics 2013 Year End Close
Emtec Inc.639 vistas
Managing and Rationalizing the Application Portfolio with CA PPM por CA Technologies
Managing and Rationalizing the Application Portfolio with CA PPMManaging and Rationalizing the Application Portfolio with CA PPM
Managing and Rationalizing the Application Portfolio with CA PPM
CA Technologies2.5K vistas
ARC's Sid Snitkin & Ralph Rio's AIM Workshop at ARC's 2009 Industry Forum por ARC Advisory Group
ARC's Sid Snitkin & Ralph Rio's AIM Workshop at ARC's 2009 Industry ForumARC's Sid Snitkin & Ralph Rio's AIM Workshop at ARC's 2009 Industry Forum
ARC's Sid Snitkin & Ralph Rio's AIM Workshop at ARC's 2009 Industry Forum
ARC Advisory Group567 vistas
Bigdata and Analytics Services - Clover Infotech por Swetha Elias
Bigdata and Analytics Services - Clover InfotechBigdata and Analytics Services - Clover Infotech
Bigdata and Analytics Services - Clover Infotech
Swetha Elias760 vistas
Tektronics casestudy- ERP Implementation por Rachna Gupta
Tektronics casestudy- ERP ImplementationTektronics casestudy- ERP Implementation
Tektronics casestudy- ERP Implementation
Rachna Gupta144 vistas
Powering performance through a tailor-made solution. por Mindtree Ltd.
Powering performance through a tailor-made solution.Powering performance through a tailor-made solution.
Powering performance through a tailor-made solution.
Mindtree Ltd. 341 vistas

Similar a Machine Learning Applications

Simple data analytics por
Simple data analyticsSimple data analytics
Simple data analyticsTaruna Sudhakar
41 vistas14 diapositivas
Best practice for_agile_ds_projects por
Best practice for_agile_ds_projectsBest practice for_agile_ds_projects
Best practice for_agile_ds_projectsKhalid Kahloot
186 vistas79 diapositivas
Real Life Lessons From an Operational Excellence Expert por
Real Life Lessons From an Operational Excellence ExpertReal Life Lessons From an Operational Excellence Expert
Real Life Lessons From an Operational Excellence ExpertMinitab, LLC
321 vistas15 diapositivas
Lace project transforming workplace learning in manufacturing printable por
Lace project transforming workplace learning in manufacturing printableLace project transforming workplace learning in manufacturing printable
Lace project transforming workplace learning in manufacturing printableFabrizio Cardinali
1.4K vistas21 diapositivas
Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile? por
Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile?Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile?
Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile?AgileNetwork
46 vistas37 diapositivas

Similar a Machine Learning Applications(20)

Best practice for_agile_ds_projects por Khalid Kahloot
Best practice for_agile_ds_projectsBest practice for_agile_ds_projects
Best practice for_agile_ds_projects
Khalid Kahloot186 vistas
Real Life Lessons From an Operational Excellence Expert por Minitab, LLC
Real Life Lessons From an Operational Excellence ExpertReal Life Lessons From an Operational Excellence Expert
Real Life Lessons From an Operational Excellence Expert
Minitab, LLC321 vistas
Lace project transforming workplace learning in manufacturing printable por Fabrizio Cardinali
Lace project transforming workplace learning in manufacturing printableLace project transforming workplace learning in manufacturing printable
Lace project transforming workplace learning in manufacturing printable
Fabrizio Cardinali1.4K vistas
Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile? por AgileNetwork
Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile?Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile?
Agile Mumbai 2022 - Ashwinee Singh | Agile in AI or AI in Agile?
AgileNetwork46 vistas
Business View of IT Applications.pdf por EverlastingSong
Business View of IT Applications.pdfBusiness View of IT Applications.pdf
Business View of IT Applications.pdf
EverlastingSong113 vistas
Bi (1) (1) por shivz3
Bi (1) (1)Bi (1) (1)
Bi (1) (1)
shivz397 vistas
Bi (1) por shivz3
Bi (1)Bi (1)
Bi (1)
shivz390 vistas
How the Analytics Translator can make your organisation more AI driven por Steven Nooijen
How the Analytics Translator can make your organisation more AI drivenHow the Analytics Translator can make your organisation more AI driven
How the Analytics Translator can make your organisation more AI driven
Steven Nooijen277 vistas
AI Maturity Levels and the Analytics Translator por GoDataDriven
AI Maturity Levels and the Analytics TranslatorAI Maturity Levels and the Analytics Translator
AI Maturity Levels and the Analytics Translator
GoDataDriven969 vistas
How to build a KPI system? por Corporater
How to build a KPI system? How to build a KPI system?
How to build a KPI system?
Corporater1.5K vistas
AI Strategy & Advance Analytics por srosen18
AI Strategy & Advance AnalyticsAI Strategy & Advance Analytics
AI Strategy & Advance Analytics
srosen18270 vistas
Challenges in adapting predictive analytics por Prasad Narasimhan
Challenges  in  adapting  predictive  analyticsChallenges  in  adapting  predictive  analytics
Challenges in adapting predictive analytics
Prasad Narasimhan793 vistas
AI Orange Belt - Session 3 por AI Black Belt
AI Orange Belt - Session 3AI Orange Belt - Session 3
AI Orange Belt - Session 3
AI Black Belt1.3K vistas

Más de Rishabh Garg

International Conference | Artificial Intelligence & Machine Learning por
International Conference | Artificial Intelligence & Machine LearningInternational Conference | Artificial Intelligence & Machine Learning
International Conference | Artificial Intelligence & Machine LearningRishabh Garg
1.4K vistas1 diapositiva
Biosensors por
BiosensorsBiosensors
BiosensorsRishabh Garg
1.6K vistas22 diapositivas
Python Library using impedance processing por
Python Library using impedance processingPython Library using impedance processing
Python Library using impedance processingRishabh Garg
1.7K vistas9 diapositivas
Fault Detection using Python por
Fault Detection using PythonFault Detection using Python
Fault Detection using PythonRishabh Garg
5K vistas27 diapositivas
Documentation and Deployment through Python Libraries por
Documentation and Deployment through Python LibrariesDocumentation and Deployment through Python Libraries
Documentation and Deployment through Python LibrariesRishabh Garg
3K vistas14 diapositivas
International Webinar - Global ID Through Blockchain por
International Webinar - Global ID Through BlockchainInternational Webinar - Global ID Through Blockchain
International Webinar - Global ID Through BlockchainRishabh Garg
6.3K vistas60 diapositivas

Más de Rishabh Garg(13)

International Conference | Artificial Intelligence & Machine Learning por Rishabh Garg
International Conference | Artificial Intelligence & Machine LearningInternational Conference | Artificial Intelligence & Machine Learning
International Conference | Artificial Intelligence & Machine Learning
Rishabh Garg1.4K vistas
Python Library using impedance processing por Rishabh Garg
Python Library using impedance processingPython Library using impedance processing
Python Library using impedance processing
Rishabh Garg1.7K vistas
Fault Detection using Python por Rishabh Garg
Fault Detection using PythonFault Detection using Python
Fault Detection using Python
Rishabh Garg5K vistas
Documentation and Deployment through Python Libraries por Rishabh Garg
Documentation and Deployment through Python LibrariesDocumentation and Deployment through Python Libraries
Documentation and Deployment through Python Libraries
Rishabh Garg3K vistas
International Webinar - Global ID Through Blockchain por Rishabh Garg
International Webinar - Global ID Through BlockchainInternational Webinar - Global ID Through Blockchain
International Webinar - Global ID Through Blockchain
Rishabh Garg6.3K vistas
International Talk on Technical Analysis por Rishabh Garg
International Talk on Technical AnalysisInternational Talk on Technical Analysis
International Talk on Technical Analysis
Rishabh Garg1.3K vistas
NAAC : Assessment & Accreditation por Rishabh Garg
NAAC : Assessment & AccreditationNAAC : Assessment & Accreditation
NAAC : Assessment & Accreditation
Rishabh Garg3.5K vistas
NAAC : Accreditation Process por Rishabh Garg
NAAC : Accreditation ProcessNAAC : Accreditation Process
NAAC : Accreditation Process
Rishabh Garg25.6K vistas
Multi purpose ID : A Digital Identity to 134 Crore Indians por Rishabh Garg
Multi purpose ID : A Digital Identity to 134 Crore IndiansMulti purpose ID : A Digital Identity to 134 Crore Indians
Multi purpose ID : A Digital Identity to 134 Crore Indians
Rishabh Garg4.9K vistas
Techno Smart Card : Digital ID for Every Indian por Rishabh Garg
Techno Smart Card : Digital ID for Every IndianTechno Smart Card : Digital ID for Every Indian
Techno Smart Card : Digital ID for Every Indian
Rishabh Garg2.7K vistas

Último

[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx por
[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx
[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptxDataScienceConferenc1
6 vistas16 diapositivas
Organic Shopping in Google Analytics 4.pdf por
Organic Shopping in Google Analytics 4.pdfOrganic Shopping in Google Analytics 4.pdf
Organic Shopping in Google Analytics 4.pdfGA4 Tutorials
16 vistas13 diapositivas
Infomatica-MDM.pptx por
Infomatica-MDM.pptxInfomatica-MDM.pptx
Infomatica-MDM.pptxKapil Rangwani
11 vistas16 diapositivas
CRM stick or twist workshop por
CRM stick or twist workshopCRM stick or twist workshop
CRM stick or twist workshopinfo828217
11 vistas16 diapositivas
Advanced_Recommendation_Systems_Presentation.pptx por
Advanced_Recommendation_Systems_Presentation.pptxAdvanced_Recommendation_Systems_Presentation.pptx
Advanced_Recommendation_Systems_Presentation.pptxneeharikasingh29
5 vistas9 diapositivas
VoxelNet por
VoxelNetVoxelNet
VoxelNettaeseon ryu
13 vistas21 diapositivas

Último(20)

[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx por DataScienceConferenc1
[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx
[DSC Europe 23] Stefan Mrsic_Goran Savic - Evolving Technology Excellence.pptx
Organic Shopping in Google Analytics 4.pdf por GA4 Tutorials
Organic Shopping in Google Analytics 4.pdfOrganic Shopping in Google Analytics 4.pdf
Organic Shopping in Google Analytics 4.pdf
GA4 Tutorials16 vistas
CRM stick or twist workshop por info828217
CRM stick or twist workshopCRM stick or twist workshop
CRM stick or twist workshop
info82821711 vistas
Advanced_Recommendation_Systems_Presentation.pptx por neeharikasingh29
Advanced_Recommendation_Systems_Presentation.pptxAdvanced_Recommendation_Systems_Presentation.pptx
Advanced_Recommendation_Systems_Presentation.pptx
neeharikasingh295 vistas
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ... por DataScienceConferenc1
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...
3196 The Case of The East River por ErickANDRADE90
3196 The Case of The East River3196 The Case of The East River
3196 The Case of The East River
ErickANDRADE9017 vistas
Ukraine Infographic_22NOV2023_v2.pdf por AnastosiyaGurin
Ukraine Infographic_22NOV2023_v2.pdfUkraine Infographic_22NOV2023_v2.pdf
Ukraine Infographic_22NOV2023_v2.pdf
AnastosiyaGurin1.4K vistas
[DSC Europe 23] Rania Wazir - Opening up the box: the complexity of human int... por DataScienceConferenc1
[DSC Europe 23] Rania Wazir - Opening up the box: the complexity of human int...[DSC Europe 23] Rania Wazir - Opening up the box: the complexity of human int...
[DSC Europe 23] Rania Wazir - Opening up the box: the complexity of human int...
[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines por DataScienceConferenc1
[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines
[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines
[DSC Europe 23] Ales Gros - Quantum and Today s security with Quantum.pdf por DataScienceConferenc1
[DSC Europe 23] Ales Gros - Quantum and Today s security with Quantum.pdf[DSC Europe 23] Ales Gros - Quantum and Today s security with Quantum.pdf
[DSC Europe 23] Ales Gros - Quantum and Today s security with Quantum.pdf
[DSC Europe 23][DigiHealth] Muthu Ramachandran AI and Blockchain Framework fo... por DataScienceConferenc1
[DSC Europe 23][DigiHealth] Muthu Ramachandran AI and Blockchain Framework fo...[DSC Europe 23][DigiHealth] Muthu Ramachandran AI and Blockchain Framework fo...
[DSC Europe 23][DigiHealth] Muthu Ramachandran AI and Blockchain Framework fo...
Chapter 3b- Process Communication (1) (1)(1) (1).pptx por ayeshabaig2004
Chapter 3b- Process Communication (1) (1)(1) (1).pptxChapter 3b- Process Communication (1) (1)(1) (1).pptx
Chapter 3b- Process Communication (1) (1)(1) (1).pptx
ayeshabaig20047 vistas
4_4_WP_4_06_ND_Model.pptx por d6fmc6kwd4
4_4_WP_4_06_ND_Model.pptx4_4_WP_4_06_ND_Model.pptx
4_4_WP_4_06_ND_Model.pptx
d6fmc6kwd47 vistas
Data about the sector workshop por info828217
Data about the sector workshopData about the sector workshop
Data about the sector workshop
info82821715 vistas

Machine Learning Applications

  • 1. Machine Learning Applications (A Human’s Guide) RISHABH GARG BITS - PILANI | GOA IIT DELHI
  • 2. Key technology aspects CRISP - DM • CRISP - DM stands for cross-industry standard process for data mining. • Most widely used and relied upon analytics process in the world (Forbes report). • Consists of 6 stages: 1. Business understanding 2. Data understanding 3. Data preparation 4. Modeling 5. Evaluation 6. Deployment PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA
  • 3. Key technology aspects PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Business Understanding • First phase of CRISP - DM • For Data Scientist 1. Key aspect is to understand the business problem and to generate value for the company. 2. ‘Value is generated by putting models into context within the business processes of a company to solve problems’. • For Business Analyst 1. Gap in the understanding of machine learning methods. Solution : Focus on the mapping of the problem and contemplate for the correct solution. Traditional methods like Business Intelligence and Six Sigma should be explored before machine learning.
  • 4. Key technology aspects PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Defining Labels • Map the problem into a data science method. • Supervised learning takes more efforts but is easier to optimize than unsupervised learning, hence more recommended. • Unsupervised learning models do not provide a qualitative measure to tune and evaluate the model. • Try to convert the supervised learning problem into a targeting problem. • While selling your business model, try to include lesser equations and mathematical language in it to be reliable.
  • 5. Key technology aspects PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Defining Labels • Answer the questions: ‘What do you want to ask the data?’ Requirements • Labels need to match the business needs The problem being worked upon must be aligned with the business goals. • Labels need to exist Situations for which very little data is available cannot be used for machine learning model training. • Labels need to be actionable On prediction about the given situation, steps should be taken as per the requirements for generation of value.
  • 6. Key technology aspects PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Performance Analysis • Involves measuring the quality of data science algorithms. • RMSE, AUC, AUPRC are meant for statistical problems and are less suited to business problems. Regression Tasks • Overestimation and underestimation should be avoided for excess material management and loss of shipment time respectively. Classification Tasks • False positives and false negatives can impact business decisions. Medical tests are a good example where false positives lead to money loss and false negatives lead to treatment delay.
  • 7. Key technology aspects PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Business Aligned Performance • Value based performance measures can be used i.e, focus on maximizing revenue for the company rather than good statistical outcomes. • Such performance measures for unsupervised learning are harder to find. Defining Success Parameters • After the project achieves a baseline, deploy and work in parallel. • Compare our project to the currently deployed models for analysis. • Else, use the naïve/ simple model approach for performance. • Use the proper methods pertaining to validation.
  • 8. Key technology aspects PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Profile Generation • This primarily involves filtering the data, cleaning the data, scrutiny of sources and data preparation for accurate results. • Detection of patterns in data for predicting labels in the machine learning model. • Establishing time period when the data is available which is different from batch running processes. • The raw data is never aggregated in such a way that the aggregated data is as appropriate for the task of machine learning as the raw data. Thus, to get the best results possible in your project, it is important to get access to the underlying data and use that for model training and evaluation.
  • 9. Business goals PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Automation • Every business carries some inefficiencies that can be replaced by high performing algorithms. Optimization • Enterprises are using artificial intelligence algorithms to optimize processes that reduce overheads and improve output. • Tightening operations means smarter budgeting and more profit. • AI can autonomously aggregate and crunch data to provide cohesion across sales and marketing. Data scrapping has been democratized and made accessible by AI.
  • 10. Business goals PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA • Data unification and customer insight are easily and autonomously accomplished with AI. The business case for AI rests on its ability to free-up human time. • Other technologies such as Smart Sensors, Microcontrollers, Real Time Dashboard, Augmented Reality using Unity etc. can be integrated to achieve smart manufacturing. Roadblocks in Implementation Questions What is in it for me ? Solution: Critically outline the business problems and define the goals. That’s not my job ? Solution: Since 70% projects are not implemented due to employee resistance (McKinsey Report). We must, first of all, clarify the goals and find the people with leadership qualities to undertake the project.
  • 11. PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Business Goals for Indian Manufacturers • Diagnosing problems and taking corrective action in time. • Enabling entrepreneurs to effectively manage multiple facilities and make them consumer centric. • Predictive maintenance and quality analytics. • Digital twin implementation (a combination of physics modelling Simulink and real data of a machine). • Big data driven processes. • Process visualization and modular production assets.
  • 12. Elevator Pitch PROJECT OF IIT DELHI | AIA | DEPT OF HEAVY INDUSTRIES, GOVERNMENT OF INDIA Indian manufacturing sector typically suffers from downtime, high latency in error rectification process, and low skilled labour which can be optimized by adopting this approach. Downtime can be tackled by predictive maintenance and RUL estimation while error rectification process can be made faster through suggestions based on real time data monitoring. More realization of profits and higher ability to use data are only the bare minimum benefits that can be received from this. (Power of 1%!!!)