THE APPLICATION OF AI IN ENTERPRISE FOR IMPROVED PERFORMANCE, INNOVATION & CUSTOMER EXPERIENCE.

Similar documents
COMPANY PRESENTATION February 2017

Company Overview and Financials. Technology Driven Consumer Finance

Results Presentation.

Company Overview and Financials. Technology Driven Consumer Finance

Mortgage Lender Sentiment Survey

Stock Market Predictor and Analyser using Sentimental Analysis and Machine Learning Algorithms

THE PROBLEM THERE IS AN INFORMATION CRISIS IN CONSUMER FINANCE LATIKA. Emilian. Alternative online lender without enough data

Impact of Digital Documents in Insurance

Industry survey - Big Data thematic review

Predictive modelling around the world Peter Banthorpe, RGA Kevin Manning, Milliman

The importance of regulating in the FinTech s world for the protection of consumers

Data-Driven Financial Conduct Regulation: the FCA s remit, datasets and research, and opportunities for collaboration

PISA 2018 released financial literacy items. This version: 06 August 2018

Artificial intelligence and customer protection in the banking and insurance industries

Data Analytics and Unstructured Data Actuaries 2.0

Inclusive InsureTech. Peter Wrede 24 February 2017

ICICI Group. November 2017

Artificial Intelligence in Insurance

FXCM Webinar Series on Algorithmic Trading

HEALTH ACTUARIES AND BIG DATA

YOUR DEFINITION OF SUCCESS IS DIFFERENT TO EVERYONE ELSE

What is AI and why do I care? Practical Applications of Artificial Intelligence for your business

FLASH TRADER APP STANDARD TERMS AND CONDITIONS

Fighting Fraud in Financial Services: three success stories

T H E F U T U R E O F C X I N B A N K I N G

Naïve Bayesian Classifier and Classification Trees for the Predictive Accuracy of Probability of Default Credit Card Clients

Future Trends 2017: The Shift Gains Momentum

LENDDO: DRIVER OF FINANCIAL INCLUSION USING DIGITAL DATA FLORENTIN LENOIR

Copyright 2008 Congressional Quarterly, Inc. All Rights Reserved. CQ Congressional Testimony SUBCOMMITTEE: DISABILITY ASSISTANCE AND MEMORIAL AFFAIRS

Application Form for Alternative Mortgage Repayments

MACHINE LEARNING IN INSURANCE

1st Seminar on Data Science & Analytics 21st July 2018 Changing Landscape of the Actuarial Profession

CHAPTER - V FINDINGS, SUGGESTIONS AND CONCLUSION OF THE STUDY

Implementing behavioral analytics to drive customer value: Insurers cannot afford to wait.

Frequently Asked Questions

1 0 P r e d i c t i o n s

PUBLIC OFFER AGREEMENT

Credit Decisioning Engines in the Cloud

Q Investor Presentation

Accenture Business Journal for India Digital Insurance: How new technologies are changing the rules of the game for a traditional industry

YOUR DEFINITION OF SUCCESS IS DIFFERENT TO EVERYONE ELSE

Mortgage Lender Sentiment Survey

Big Data Analytics and Insurance

HedgeChatter Case Study: Stock Price Manipulation Detection

- Digital Tax Administration System -

International Journal of Advance Engineering and Research Development REVIEW ON PREDICTION SYSTEM FOR BANK LOAN CREDIBILITY

Attract and retain more high-quality customers while reducing your risks.

FOLLOWING GLOBAL TRENDS, OR LEADING AN INDUSTRY LOCALLY?

NEXT GENERATION ONLINE BANKING OVERVIEW

Q Investor Presentation August 1, 2017

Ez Trading Platform. Alltogether, traders are able to perform a more comprehensive probability analysis of their trades.

PUTTING YOUR INNOVATION IN THE SPOTLIGHT

FOLLOWING GLOBAL TRENDS, OR LEADING AN INDUSTRY LOCALLY?

Interim results. for the six months to 30 September Company Registration Number

FOLLOWING GLOBAL TRENDS, OR LEADING AN INDUSTRY LOCALLY?

Understanding Your FICO Score. Understanding FICO Scores

Moderator: Ann Weber, JD. Presenters: Dan Adamson Angela Nelson

SELECTION BIAS REDUCTION IN CREDIT SCORING MODELS

A Social Landlords Guide to Reducing Rent Arrears

Implementing the Expected Credit Loss model for receivables A case study for IFRS 9

Session 2. Leveraging Predictive Analytics for ERM

AIB Graduate Current Account Application Form

RAISON.AI. Investment proposal (Pitch Deck )

Background for Case Study Used in Workshop

There are 3 pricing options available for Prestige Banking to help you choose the best option for you:

UK Business and Charity Digital Index 2018 Appendix. The fifth edition Benchmarking the digital capability and skills of UK SMEs and charities

Based on the audacious premise that a lot more can be done with a lot less.

Privacy Notice. Please read this privacy notice carefully as it explains how we use your personal information.

1H 19 Investor Presentation February 2019

Reduced Repayment Application Form For Alternative Mortgage Repayments

SHARETHIS FINANCE STUDY

MANAGING CREDIT RISK IN CHANGING TIMES

Customer Privacy Notice Edition

There are 3 pricing options available for Prestige Banking to help you choose the best option for you:

Stock Prediction Using Twitter Sentiment Analysis

GDPR: The future of marketing and commercialisation of data. Alexander Brown & Matt Dyer, Simmons & Simmons

Machine Learning in High Frequency Algorithmic Trading

INTERIM RESULTS For the six months ended 31 December 2017

FIGHTING AGAINST CRIME IN A DIGITAL WORLD DAVID HARTLEY DIRECTOR, SAS FRAUD & FINANCIAL CRIME BUSINESS UNIT

YouGov Survey Results

Fintech List Camino Financial Climb Credit SoFi Blend Labs Even

Keyword: Risk Prediction, Clustering, Redundancy, Data Mining, Feature Extraction

Risk and Risk Management in the Credit Card Industry

Our Privacy Notice for UK business customers. Effective from 25 May 2018

AIB Personal Current Account Application Form - Sole

Lending with a Purpose

There are 3 pricing options available for Prestige Banking to help you choose the best option for you:

Are New Modeling Techniques Worth It?

Digital insurance: How to compete in the new digital economy

WHITE PAPER. Tech Trends in Debt Collection Software that are Personalizing the Debt Collection Process and Helping Enterprises Protect Their Brands

Frequently Asked Questions

Description of the general aggregation scheme How do I perform trading transactions?... 6 REST API... 7 FIX API FortFC services...

GENERAL TERMS AND CONDITIONS

XWIN CryptoBet SUMMARY

AIB Personal Current Account Application Form - Joint

Capturing the value of data

Lovar. Artificial Intelligence Investment Platform. White Paper

Banking Monitor - Edition 2. July Overview

Data Driven Decision Making

ASX ANNOUNCEMENT. Commentary on 2017 and H Financials Part 1

Transcription:

1 THE APPLICATION OF AI IN ENTERPRISE FOR IMPROVED PERFORMANCE, INNOVATION & CUSTOMER EXPERIENCE F E B R UA RY 2 0 1 8

2 Company overview.

3 is living the Megatrends right here in Africa.

MyBucks Technology. 4 Artificial intelligence Big data Best EU Financial Inclusion Company 2017 Chatbots Cloud Open API s

5 Artificial intelligence.

A.I.? 6 Point of singularity. According to this hypothesis, an upgradable intelligent agent (such as a computer running software-based artificial general intelligence) would enter a 'runaway reaction' of self-improvement cycles, with each new and more intelligent generation appearing more and more rapidly, causing an intelligence explosion and resulting in a powerful superintelligence that would, qualitatively, far surpass all human intelligence.

Segmentation algorithms What is A.I.? Age prediction example https://how-old.net/ Required skill set 7 Actuarial Targeted marketing Retention and win-back Understanding customer behaviour Statistics Computer Science Maths Unstructured data, Scraping, Natural language, Social data mining, Processing BENEFITS WORKING-CONDITION GRIT FOCUS EXTREME HOURS EXCEPTIONAL SCHEDULE LOCATION WORK ADVANCEMENT RELATIONSHIPS SALARY HOURS LUNCH IDEAS PEOPLE FOLKS CHARTER FOLKS FUTURE Machine learning Classification algorithms Regression Commute distance Gender Occupation Amount of cars Home owner Region Marital status Children Survival analysis Time series analysis Advanced sampling Provisioning Campaign design & evaluations Forecasting Segment analysis Market modeling Behavioural modelling Age Predict default Fraud detection Credit scoring Risk management

A.I. @ MyBucks. 8 AI for Innovation AI for improved customer experience Tess A.I. AI for improved operations 70% 60% 50% 40% 30% 20% 10% Percentage Uptake vs. Probability of Uptake Dexter Jessie 0% 0.1-0.5 0.5-1.0 Probability of Uptake

9 AI for improved operations.

Optimising operations using AI: two big use cases at MyBucks. 10 DE X TE R AI based fraud detection and prevention JESSIE AI based credit risk model

How? 11 Start with Data.

How? 12 A model is trained and evaluated on existing data. Train. Test. Closed loans (known outcome) together with all the relevant attributes that we will use to make the prediction are used for training. We don t use all the data for training: we keep out a random selection of loans and use it to evaluate the model. Now we can adjust the algorithm parameters, and try different attributes to achieve a better model. Approve Decline

The decision boundary. 13 Threshold: 50% 2% 40% 80% A machine learning model returns a PROBABILITY of default. We have to decide on a threshold value, above which the loan will be declined. Clients with a probability of default higher than the threshold are denied credit.

Using A.I. Unlimited number of factors can be considered simultaneously. 14 Country A Country B Classifier ability to distinguish good loan from bad loan High threshold age days_since_last_loan GrossSalary Amount Deductions application_day_of_m loan_num failed_installment_cumcount SalaryDateDay extrapayment_cumcount installment_cumcount nrloanapps application_hour_of_d MotivationType cumnum_active_good application_day_of_w BankRefId cumnum_goodloans Title MaritalStatus Amount age ave_amt_in_trans_mth days_since_last_loan ave_min_bal_mth ttl_no_of_trans loan_num RiskScore ave_amt_out_trans_mth failed_installment_cumcount cumnum_goodloans application_hour_of_d amt_of_new_loans MotivationType ave_no_of_trans_mth max_inc Declined nrloanapps application_day_of_m no_of_new_loans Number Number 0 Truth: Good loan Good loan Classifier prediction Low threshold Truth: Good loan Good loan Truth: Bad loan Truth: Bad loan Classifier prediction Bad loan Bad loan 0 1 Classifier prediction Classifier prediction Good loan Truth Bad loan Good loan 450 100 Bad loan 50 400 Low false alarm rate Good loan Truth High miss rate Bad loan Good loan 400 75 Bad loan 100 425 High false alarm rate Low miss rate

Visualising AI. 15

Model improvement over time. 16 V5 Gini: 38% V6 Gini: 42% mploansent age mpavgbalance mpwithdrawn Amount mptransfer mpttlamount Dependents days_since_last_loan application_hour_of_d mpavgbalance age mpttlamount application_hour_of_d mpdeposit mpwithdrawn mpbought mpnrtransactions mpsent mpunknown Default Rate V12 Gini: 54% V15 Gini: 56% age application_day_of_m mpavgbalance age mpavgbalance mpwithdrawn 201610 201611 201612 201701 201702 201703 201704 201705 201706 mpwithdrawn mpttlamount mpttlamount DurationRecentOutgoingCalls Jessie Control Group mploansent NrRecentIncomingCalls DurationRecentIncomingCalls mploansent LoginLongitude application_day_of_m DurationRecentOutgoingCalls NrRecentOutgoingCalls DistinctRecentCallNumber DurationRecentIncomingCalls

Dexter AI based fraud detection. 17

18 AI for Innovation.

Haraka. 19 1 2 3 4 Client register with his/her Facebook details via Android smartphone. An Artificial Intelligence (A.I.) algorithm analyse data from the client s phone to determine the client s affordability and predict credit risk. Funds are disbursed using the client s Mobile money account. Our point system rewards clients that display positive repayment behaviour, and incentivises clients to share the app with friends. Page 10

20 AI for improved Customer Experience.

Use cases: Virtual assistant (Tess). Text-based virtual assistant 21 Lending: Assist with loan applications by predicting intent and interpreting queries over text channels, such as instant messaging apps. Collections: Assist with collections by engaging with customers over text channels, such as instant messaging apps. Banking: Virtual banker e.g. check balances and perform transaction in natural language e.g. Tess what is my balance? Insurance: Assist with claims, quotations, customer service and sales. Customer support on all channels: Assist with frequently asked questions on all channels e.g. website, apps, messaging apps etc. Onboarding: Assist with onboarding on all channels across lending, banking and insurance.

Automated Customer Relationship Management (CRM). 22 Predicting the next action of a client. Probability that a client will drop-off Predicting the best engagement option. E.g., if likely that client will drop-off What channel to use (email, sms, whatsapp, pop-up, etc.) When to engage What message to send

23 Thank you. Dr. Richard van der Wath Group Chief Data Officer Mobile: +27 71 384 3119 Phone: +352 2088 2123 Email: Richard@mybucks.com

Disclaimer. 24 Please note: This presentation is strictly confidential and is not to be duplicated or distributed without the written approval from MyBucks.