Russia - JUNE 2020 LIME LOANS - Mintos
←
→
Page content transcription
If your browser does not render page correctly, please read the page content below
Russia
LIME LOANS
MULTI-MARKET ONLINE CONSUMER LENDING
JUNE 2020
LIME ©2020
CORPORATE MILESTONES
Machine Learning lab
Russia Poland South Africa Installment loans founded with local technical
Joined Mintos Mexico Insurance
Launch Launch Launch introduced P2P Platform Launch introduced
university
4/2014 12/2015 7/2016 4/2017 7/2018 12/2018
6/2017 5/2019
100k 200k 300k 400k 500k
ORIGINATIONS, Q Loans Loans Loans Loans Loans
6/2016 4/2017 10/2017 4/2018 5/2019
Corporate partners
MobileScoring
LIME ©2020Established in 2013
132 employees
Top-10 rated by RAEX on
Russian market 51M EUR issued in 2019
8 years on market
Internal fintech tools
automating business
processes
Year 2019
Effective interest rate Vintage total
recovery 6Month
PDL 363% 127%
Installments 235%
LIME ©20202 MAIN PRODUCTS: PDL AND
INSTALLMENT LOANS
PDL INSTALLMENTS
To get money for shortterm goals Loans with annuity schedule up
to 6 month
Partnered cross products
Insurance Virtual cards Payment cards
Easy and fast from any point for
RU citizens
LIME ©2020BENEFITS OF INSTALLMENT LOANS
Annuity predictable Approval of higher quality clients
payment schedule:
A set term: six or twenty four weeks:
Only clients with a high credit score and meeting
the pool of additional criteria are approved for
installment loans
A set sum of loan: from ~ 320 to ~ 900
euros:
Significantly lower level of fraud
Due to predictable annuity payment
schedule clients definitely know when
and in what amount to make a payment
LIME ©20202019 HIGHLIGHTS
YonY
Originations up Originated 51m EUR in 2019, versus 34m in 2018.
By 50%
In May 2019, insurance policies were integrated into PDL and
Introducing a new type of
installment. Thus, share of policies in total issuance amounted to 5%.
product: insurance
The total revenue from insurance reached 2.5m EUR in 2019.
Introducing a cascade of A cascade of scoring models has been introduced for early rejection of the
scoring models riskiest customers and savings on the cost of paid data sources
LIME ©2020LENDING KPIS - RUSSIA
Annual Quantities and Values of Loans Average Loan Size (EUR) Loans share
Total
Qty of % changes %
originations Blended PD Instalment
loans changes
(EUR)
2014 7 769 450 219 2014 60 60 31%
2015 50 782 554% 2 465 398 448% 2015 49 49
2016 88 614 74% 5 010 293 103% 2016 57 57 69%
2017 163 493 85% 14 172 854 183% 2017 87 78 304
2018 295 776 81% 34 377 067 43% 2018 122 82 332
2019 340 066 15% 2019
Instalment PDL
51 584 176 50% 151 121 333
LIME ©2020LENDING KPIS - RUSSIA
Cumulative Recovery (as % of Originations), Borrower Demographics
*figures as of 31 December 2019 at historical FX,
*money-weighted average
Originations Women Men
2019 M1 M2 M3 M4 M5 M6 M12
(EUR) % age % age
2014 47.6 29 52.4 33
Q1 16 357 528 105 112 116 118 119 120 121
2015 49.9 33 50.1 36
2016 52.8 33 47.2 36
Q2 13 011 102 103 112 116 119 121 122 122
2017 52.7 32 47.3 35
Q3 10 902 362 101 111 116 119 121 123 2018 55.7 32 44.4 35
2019 44,59 30 55,41 33
Q4 9 664 119 107 116 121 124 126
LIME ©2020PAYMENT FLOW
Outgoing (weekly total) Incoming (weekly total) Trendline
Before During pandemic Out of the crisis
NPL increased Full repayment of debt to investors
Planned increase of originations
Originations decreased Restructuring of overdue loans
Planned introduction of new Increasing originations
products Funding deficit on P2P
platforms Reduced fixed costs
LIME ©2020LIME CREDIT GROUP DEMONSTRATES STABLE
GROWTH ON THE RUSSIAN MARKET
LCG is growing in the volume of loans to customers without reducing the Despite the significant growth in originations, LCG managed to reduce
quality of the loan portfolio: 2019 vs. 2018 – increase 50% unrecovered principal across the year
* Originations, thous. Euro 0.35 Unrecovered principal* 180 days
35,00
51 584 0.30
30,00
Forecast
0.25
34 377 25,00
Trend
0.20
20,00
0.15
13 135 15,00
0.10
4 168 10,00
5,00 Jan’20 Feb’20 Mar’20 Apr’20 May’20 Jun’20 Jul’20 Aug’20 Sep’20 Oct’20 Nov’20 Dec’20
2016 2017 2018 2019 0,00
The LCG demonstrates a stable growth rate: the revenue 2019 increased by Despite a tightened regulatory environment in 2019, the company maintains
nearly 2X compared with 2018 it’s Total Recovery and Profitability
* Revenue (interest income etc)., thous. Euro Total Recovery 180 days * by generation of loans
128,00
48 315 Forecast
1.30
126,00
24 577 1.25
124,00 Trend
1.20
122,00
12 568 1.15
120,00
3 885 FORECAST 1.10
118,00
1.05
116,00
2016 2017 2018 2019 Jan’20 Feb’20 Mar’20 Apr’20 May’20 Jun’20
114,00 Jul’20 Aug’20 Sep’20 Oct’20 Nov’20 Dec’20
* Implies vintage analysis by loan generations: the financial results of clients (took a loan, for example, in Feb’19) in 180 days 10MARKET OPPORTUNITY
Consumers around the world lack access to Huge Total Addressable Markets
Annual lending in these markets is significant – hundreds of millions
reliable credit that they want and deserve. This is
and up to billions annually. With their automated processes and low
especially true in emerging markets, for historical cost-base, Lime operations don't have to capture much of these
and other reasons. markets to be profitable.
5 Years of Experience Since early 2014, Lime have
Traditional lenders are reluctant to address this
proven that their on-line lending platform can be set up
demand because default rates are high, loan amounts
quickly and cheaply, tuned to the local specifics, and be
are low, but processing costs are similar to other
configured to address any target market and product
products.
mix.
Unsecured Short-Term (< 6 month) Consumer Lending annual volume (in USD Millions):
Brazil
Mexico Spain Russia Korea
South
Peru Greece Vietnam Chile Philippines Thailand
Africa
224 227 228 280 340 365 461 1300 1400 1500 1510 2000
Sources: South Africa National Credit Regulator, “Payday lending market investigation” 2015 UK CMA, “The State of Online Short Term Lending” 2015 Bretton Woods, World Bank WDI, Lime Capital
ResearchAUTOMATED SCORING
5 5
3
Auto approve
Scoring for Leads 2 Outstanding
4 Collection
scoring
Tariff assignment
Credit application Credit scoring 3
1 Manual
verification 5
Credit robot & 3
Repayment Court
Antifraud model Auto refuse
Collection
scoring
7
Blocking Short & Long term review
LIME ©2020RISK MATRIX
Lime Credit group manage risks on all of the
operation stages. Main risks mitigation strategy
3 connected to solvency assessment. It is important
to mitigate economy risks too
1 2
1 Fraud risk
Solvency
5 assessment risks 2 Credit risk
4 Economy risks
6 3 Model mistake risk
4 Loyalty risk
5 Collection risk
6 Lost profit risk
Low Middle High Probability
LIME ©2020CREDIT ROBOT &
ANTIFRAUD MODEL
Firstly, applications are processed by the Credit Robot’s checkpoints to block the criminal and clients with false data
Credit robot performs static checks on What we do for improvement
customer data and loan applications for
their authenticity based on credit bureaus • Develop potential checkpoints
data
• Retro-testing checkpoints for
target results to confirm efficiency
Antifraud system is based on ML
algorithms model that performs dynamic
verification based on open sources data • Periodically re-analysis the
(blacklist and etc.) checkpoints.
Checkpoints examples
• terrorists • match table • name from filled bank account
• risk PANs / bill numbers • age limits owner differs from name filled in
• loosed document • data from credit bureaus application form
LIME ©2020CREDIT SCORING ML SERVICE
Automatic estimation for the probability of loan repayment by this client based on ML algorithms
Step-by-step estimation advantages
Services performs step-by-step estimation result of
this model is the clients score that normalized from 0 Less mistakes due to fraud
to 1. Client’s score is a probability of repayment blocking by Credit Robot and
Anti Fraud Model
1 On the first step model: 2 The second consists few iterations Less money spend on pay
data
• Use only free data sources At each iteration model use new NON FREE
• Rating clients on these data data source and:
• Passes on the next stage only • Rating clients on these data
clients with good rating • Passes on the next stage only clients with
Scoring model could be
good rating
… then goes to the next one
retrained on the better quality
train
LIME ©2020CREDIT SCORING ML SERVICE
Combination of different data sources increases model’s quality rapidly
- Bank transactions’ sources
- Black lists
• Terrorists - Credit history bureaus
• Extremists
- Anti-fraud sources
- The Federal Tax Service reports - Mobile operators
• complex to get sensitive data
- Clients application
- Social networks data
- Intersection of personal data of the
application with the current database
- UI-telemetry
LIME ©2020ADDITIONAL DATA SOURCES AND
MANUAL VERIFICATION
Verifiers complement application with manually found data so model could make a concrete decision
Manual verification process
1 Verifiers review client’s applications
Auto approve and look through needed data
Model makes this decision
when It is hard to tell is 2 Personal verification that could not be automated.
this client reliable or not: Mostly calls to clients or to client’s employer/ confidant
chances are the same
Manual
verification 3 Fulfilling the or correction the application data
So model could make
4
unequivocal decision to lend or not on fullest data set
Auto refuse
LIME ©2020PERSONAL TARIFF ASSIGNMENT PROCESS AND LOYALTY PROGRAM
Lime credit group mitigate loyalty risk by offering individual terms and discounts to clients
Important to give clients what they need so they’ll stay loyal and regular. In other case clients will prefer competitors
services
With every successful paid loan client
Individual tariff Dynamic calculation sums-percent
1 2 rise available sums and decline rate for
assignment rates in according to score
next loan
Most attractive terms for the first loan With every successful 15 days loan client
1 allows to 2
Loyalty program rises discount rate for the next loan
get acquainted with our services
Behavioral We use RFM behavioral analysis to
marketing drive desirable behavioral
General idea: regularly make optimization: retro-test for previous credits by using all the combinations sum-percent-score match table to
maximize received profit \ complex metric
Hypothesis: independence of repayment statistics from sum in limits of product type
LIME ©2020COLLECTION SCORING AS
OUTSTANDING’S MANAGEMENT
Collection scoring provides most efficient strategies for non-performing clients
Collection scoring gives probability of repayment the outstanding by Collection scoring advantages
this concrete client. Collection score provides the communication
Automation:
strategy that is the most efficient for this deb loan.
Machine learning services is
way more efficient then
1 First collection score: personal estimates
Provides insides for debtor’s communication strategy
• On which day to start the automatic newsletter
Cost optimization:
• On which day to start personal calls
• How much unfulfilled promises could we take before taking Collection scoring allows to
case to the court reduce excessive funds spend
In progress Second collection score – court score: on personal communication
Provides insides for taking case to court
• Trial requests additional costs
• How old should be debt to take this additional costs
LIME ©2020REHABILITATION PROCESS FOR
REJECTED CLIENTS
Review client’s relatability allows to satisfy the maximum requests and get maximum profit
Client could be blocked on different stages. It is important to monitor client’s reliability over time. If, for example, a client will fill
an application with correct data, relatability will grow and the model will be able to give more positive decisions. Not tracking
such changes could lead to losses.
30
days
Credit application
Review
90
days
Review
1
year
Review
LIME ©2020COLLECTION PROCESS
On improvement
Automated Pre-collection
Reminders Phone calls Restructuring offer Debt sale
Decision Zone
Court (semi-automatic
-2 0 15 30 45 60 75 90 procedure)
Outsourced debt
collection
Will be SMS On
E-mails improvement Letters
automated
Collections Success In Numbers
Early On timePRODUCT DEVELOPMENT ROADMAP
Lime's expertise is in the consumer credit silo, which is
highly profitable and funds our geographic expansion Typical The client base can be leveraged through partnership deals with
and product development: Loan Terms providers of other financial services.
(months)
The platform can be leveraged by adapting it's decision making
Partner products: Virtual Credit Cards >12M power and distribution flexibility to similar businesses.
- Insurance – Auto, Health,
Property, Travel Revolving Credit 12M
- Vacations / Travel Layaway • Chat-bot Government / NGO
Installment Loans 4M Employee • Voice-bot Sponsored Specific
programs
Background Purpose MicroFinance
• Loyalty program
- Auto Title Loan Instant Loans 1M
Tenant • Collection scoring
Branded Credit Cards >12M Credit • ML scoring
Expected Check • RFM model
Consumer Credit Information Services Development Credit
Leverage Client Base Leverage Platform
LIME ©2020FOUNDERS
Alexey Nefedov Stanislav Sergushkin
CEO / Co-founder COO / Co-founder
Before co-founding Lime, Alexey spent a few Stanislav and Alexey met at university in the
years working as an implementation UK, and since both of them had prior
consultant for an enterprise applications experience as underwriters, their ideas
developer and as a credit card underwriter at about a better on-line lending platform
a major Russian bank. In his day-to-day role quickly came together. As Lime's COO,
as CEO of Lime, Alexey sets strategic Stanislav handles day-to-day operations in
priorities, is the chief system architect, addition to leading product development
makes most HR decisions, and oversees legal and territorial expansion. The business
and regulatory compliance. In the three years process flows, risk management procedures,
since its establishment, Alexey has spent and scoring models in use at Lime are all
time in pretty much every role in the products of Stanislav's guidance.
company from collector to underwriter to
programmer.
LIME ©2020LIME LOANS
MULTI-MARKET ONLINE CONSUMER LENDING
Contact:
Kevin Hurley
CFO
k.hurley@limecreditgroup.com
LIME ©2020LEGAL DISCLAIMER
IFRS Financial Information Risk and Uncertainties that May Affect Performance
In addition to the unaudited financial information prepared in conformity with This presentation contains forward-looking statements about the business,
International Financial Reporting Standards (“IFRS”) included in this financial condition, strategy, and prospects of Lime Capital Partners Inc (further
presentation and its accompanying supporting documentation, the Company “Lime” or “the Company”). These forward-looking statements represent the
provides details of its operations, calculations, and financial statements that are current expectations or, in some cases, forecasts of future events and reflect the
not considered measures of financial performance under IFRS. Management views and assumptions of Lime's management with respect to the business,
uses these non-IFRS financial measures for internal managerial purposes and financial condition and prospects of the Company as of the date of this release
believes that their presentation is meaningful and useful in conveying an and are not guarantees of future performance. Lime's actual results could differ
understanding of the activities and business metrics of the Company’s materially from those indicated by such forward-looking statements because of
operations. Management believes that these non-IFRS financial measures various risks and uncertainties applicable to its business. These risks and
reflect an additional way of viewing aspects of the Company’s business that, uncertainties are beyond the control of Lime, and, in many cases, the Company
when viewed together with with the Company’s IFRS results, may provide a cannot predict all of the risks and uncertainties that could cause its actual results
more complete understanding of the factors and the trends affecting the to differ materially from those indicated by the forward-looking statements.
Company’s business. Management provides such non-IFRS financial When used in this presentation, the words "believes," "estimates," "plans,"
information only to enhance readers' understanding of the Company’s IFRS "expects," and "anticipates", as well as similar expressions or variations as they
consolidated financial statements. Readers should consider the information in relate to Lime or its management are intended to identify forward-looking
addition to, but not instead of, the Company’s financial statements prepared in statements. Lime cautions you not to put undue reliance on these statements.
accordance with IFRS. This non-IFRS financial information may be determined Lime disclaims any intention or obligation to update or revise any forward-looking
or calculated differently by other companies, limiting the usefulness of those statements after the date of this release. A more in-depth, though not complete,
measures for comparative purposes. discussion of some of the risks and uncertainties that may affect Lime's future
performance is included as an appendix to this presentation
LIME ©2020You can also read
