ADVANCED TOOLS IN REAL TIME ANALYTICS
AND AI IN CUSTOMER SUPPORT
TOM ŽUMER
MILAN SIMAKOVIĆ
AGENDA
• Lambda architecture
• Stream processing pipeline
• Apache Kafka
• Realtime data processors
• Graphic ETL tools
• AI in Customer support
AGENDA
www.ibis-instruments.com
What we do
SOFTWARE
DEVELOPMENT
Our products
SOLUTIONS IPI – Ibis
Performance
Insights
FOI -
Field
Operation
s
Insights
Description
Ibis
Risk Analytics
Technologi
es
iCEM Mobile Network
Advanced
Analytics (5G)
Machine
Learning use cases
Ibis
Data Lake
E2E Network
monitoring and
analytics solution.
Deep monitoring for:
Docsis/HFC, IPDR, PNM,
WiFi optimization, MPL
S,
UPS, DSL, GPON, TR069,
Mobile Network.
Centralized
monitoring and
control of Field
Operations.
Analytics over
measurement data.
Risk analysis for
banks:
- Calculation of
IFRS9 in one
system.
-Scoring/Rating
tool.
- EWS tool.
Ibis Data Lake - a
reference
architecture for
implementing
Data Lake by Ibis
best practice,
allows data-based
innovation.
A modern solution
for managing
customer
experience based on
analytics for
Telecommunication
providers and other
industries.
An advanced
mobile network
analysis, with a
focus on today's
and future
challenges.
Realization of
different use cases
based on machine
learning such as:
- Churn prevention,
- Smart pricing
- Next best offer.
Work in progress
Usecases
DWH
Card
transactions
Shopping
Realtime
processing
Overdraft
?
Credit
card?
Realtime credits – Is it
possible?
LAMBDAARCHITECTURE
LAMBDA ARCHITECTURE
DWH
Data
ingestion /
integration
Data storing (Data lake) Data access and
processing
Data visualization
Realtime
Real-Time
Stream Processing
Data lake (HDFS)
NoSQL (HBase)
Relational (Kudu)
Data analytics

Batch processing
(MapReduce, Hive Pig,
Spark, Hue)
SQL (Impala)
Search (SOLR)
Machine Learning, Data
mining, Statistics
Collaboration,
Data exploaration
Batch
Shell
Python Perl
Custom
Visualizations
CRM
Campaign
mgmt
SMSC
Call center
IVR
Realtime Integrations
BI
CDH
Unified Services (Resource management – YARN, Security – Sentry and Record) Kerberos – authentication
Workflow scheduler
Integrated data management and governance – Cloudera navogator Cluster management – Cloudera
manager
IBIS DATA
LAKE ARCHITECTURE
A STREAM PROCESSING PIPELINE
ASTREAMPROCESSINGPIPELINE
collect log analyze serve and store
source: Pluralsight
REAL TIME PROCESSING
• Process continuous data streams
• Reduce time increase
information value
• Filter only useful bits
• Streaming is a much more natural
model
REALTIMEPROCESSING
APACHE FLINK
• Framework and distributed processing
engine
• Process Unbounded and Bounded Data
• Leverage In-Memory Performance
• Building Blocks for Streaming Applications
• How does Flink support data pipelines?
APACHEFLINK
APACHE BEAM
APACHEBEAM
• open source unified programming model to define and
execute data processing pipelines
ETLs be like…
ETLsbelike…
NifiFlow
TomŽumer
AGENDA
•Implementation of AI in customer support
www.creapro.si
EKWB
• EKWB is a premium liquid cooling manufacturer
• Founded in 1999 by Edvard König
• Their products are available in more than 30 countries worldwide
• EKWB offers a full range of products for end users and enterprise as well
• Some of the products are cooling systems (CPU and GPU), fittings, radiators,
water blocks, reservoirs, pumps
EKWB
• EKWB uses Zendesk customer
support software
• It offers interactions between
customers and EKWB support team
through so called tickets
• Customers create tickets where they
describe their questions with EKWB
products/orders
Zendesk
ZENDESK
Tickets
• Tickets are resolved by EKWB support groups
• There are two EKWB support groups:
• Technical
• Shipping
• There are three different categories of tickets:
• Technical
• Shipping
• AND GENERAL!!!
TICKETS
Challenges
Manual assignment of tickets to
support groups
Faster reply time to more critical
tickets
Which agent is going to reply
unassigned tickets
CHALLENGES
Solution
• Automatic ticket classification to Support or Technical
team
• Calculation of ticket priority
• Algorithm for automatic ticket assignment
SOLUTION
IS IT REALLY ?!?
84%
57%
25%
91%
55%
30%
Workflow process
WORKFLOWPROCESS
Support Team Classification
• Challenges:
• Preparing training and test set
• Validation of results
• Implementation of model in working process
• It‘s a NLP problem!
• We used BERT embeddings for text
representations
• Model classifies tickets with SVM algorithm
• We achieved balanced accuracy of 89,33%!
SUPPORTTEAMCLASSIFICATION
AND WE ARE IMPROVING
IT!!!
Automatic Priority Calculation
• Goal was to prepare ticket priority
evaluation
• EKWB team had to mark tickets on
scale 1-5 for few months!
• Tickets need to be ranked by their
priority so that tickets with higher
priority are solved sooner
• QUESTION: classification || regression?
• Model evaluates ticket on scale 1-100%
PRIORITYCALCULATION
4 5
6,4% 40,2
%
5
34,7%
Automatic Agent Assignment
• Who is going to solve next ticket?
• Person with the least tickets?
• Person with least high priority tickets?
• How to know which agent is active?
• Our system smartly assigns tickets to one of
active agents
• Trying to find balance
AGENTASSIGNMENT
Future Work
• Dockerize everything!!!
• Automatic cancelation of orders based on tickets
• Connection with ERP system
• Automatic responses
(or at least semi automatic)
• DEEP THOUGHT
*Hitchhikers guide to the galaxy
FUTUREWORK
THANK YOU.
Automation is driving the decline
of banal and repetitive tasks.
- Amber Rudd

Advanced tools in real time analytics and AI in customer support - Milan Simakovic, Tom Zumer

  • 1.
    ADVANCED TOOLS INREAL TIME ANALYTICS AND AI IN CUSTOMER SUPPORT TOM ŽUMER MILAN SIMAKOVIĆ
  • 2.
    AGENDA • Lambda architecture •Stream processing pipeline • Apache Kafka • Realtime data processors • Graphic ETL tools • AI in Customer support AGENDA www.ibis-instruments.com
  • 3.
  • 4.
    Our products SOLUTIONS IPI– Ibis Performance Insights FOI - Field Operation s Insights Description Ibis Risk Analytics Technologi es iCEM Mobile Network Advanced Analytics (5G) Machine Learning use cases Ibis Data Lake E2E Network monitoring and analytics solution. Deep monitoring for: Docsis/HFC, IPDR, PNM, WiFi optimization, MPL S, UPS, DSL, GPON, TR069, Mobile Network. Centralized monitoring and control of Field Operations. Analytics over measurement data. Risk analysis for banks: - Calculation of IFRS9 in one system. -Scoring/Rating tool. - EWS tool. Ibis Data Lake - a reference architecture for implementing Data Lake by Ibis best practice, allows data-based innovation. A modern solution for managing customer experience based on analytics for Telecommunication providers and other industries. An advanced mobile network analysis, with a focus on today's and future challenges. Realization of different use cases based on machine learning such as: - Churn prevention, - Smart pricing - Next best offer. Work in progress
  • 6.
  • 7.
  • 8.
    Data ingestion / integration Data storing(Data lake) Data access and processing Data visualization Realtime Real-Time Stream Processing Data lake (HDFS) NoSQL (HBase) Relational (Kudu) Data analytics Batch processing (MapReduce, Hive Pig, Spark, Hue) SQL (Impala) Search (SOLR) Machine Learning, Data mining, Statistics Collaboration, Data exploaration Batch Shell Python Perl Custom Visualizations CRM Campaign mgmt SMSC Call center IVR Realtime Integrations BI CDH Unified Services (Resource management – YARN, Security – Sentry and Record) Kerberos – authentication Workflow scheduler Integrated data management and governance – Cloudera navogator Cluster management – Cloudera manager IBIS DATA LAKE ARCHITECTURE
  • 9.
    A STREAM PROCESSINGPIPELINE ASTREAMPROCESSINGPIPELINE collect log analyze serve and store
  • 11.
  • 12.
    REAL TIME PROCESSING •Process continuous data streams • Reduce time increase information value • Filter only useful bits • Streaming is a much more natural model REALTIMEPROCESSING
  • 13.
    APACHE FLINK • Frameworkand distributed processing engine • Process Unbounded and Bounded Data • Leverage In-Memory Performance • Building Blocks for Streaming Applications • How does Flink support data pipelines? APACHEFLINK
  • 14.
    APACHE BEAM APACHEBEAM • opensource unified programming model to define and execute data processing pipelines
  • 15.
  • 17.
  • 18.
    TomŽumer AGENDA •Implementation of AIin customer support www.creapro.si
  • 19.
    EKWB • EKWB isa premium liquid cooling manufacturer • Founded in 1999 by Edvard König • Their products are available in more than 30 countries worldwide • EKWB offers a full range of products for end users and enterprise as well • Some of the products are cooling systems (CPU and GPU), fittings, radiators, water blocks, reservoirs, pumps EKWB
  • 20.
    • EKWB usesZendesk customer support software • It offers interactions between customers and EKWB support team through so called tickets • Customers create tickets where they describe their questions with EKWB products/orders Zendesk ZENDESK
  • 21.
    Tickets • Tickets areresolved by EKWB support groups • There are two EKWB support groups: • Technical • Shipping • There are three different categories of tickets: • Technical • Shipping • AND GENERAL!!! TICKETS
  • 22.
    Challenges Manual assignment oftickets to support groups Faster reply time to more critical tickets Which agent is going to reply unassigned tickets CHALLENGES
  • 23.
    Solution • Automatic ticketclassification to Support or Technical team • Calculation of ticket priority • Algorithm for automatic ticket assignment SOLUTION IS IT REALLY ?!? 84% 57% 25% 91% 55% 30%
  • 24.
  • 25.
    Support Team Classification •Challenges: • Preparing training and test set • Validation of results • Implementation of model in working process • It‘s a NLP problem! • We used BERT embeddings for text representations • Model classifies tickets with SVM algorithm • We achieved balanced accuracy of 89,33%! SUPPORTTEAMCLASSIFICATION AND WE ARE IMPROVING IT!!!
  • 26.
    Automatic Priority Calculation •Goal was to prepare ticket priority evaluation • EKWB team had to mark tickets on scale 1-5 for few months! • Tickets need to be ranked by their priority so that tickets with higher priority are solved sooner • QUESTION: classification || regression? • Model evaluates ticket on scale 1-100% PRIORITYCALCULATION 4 5 6,4% 40,2 % 5 34,7%
  • 27.
    Automatic Agent Assignment •Who is going to solve next ticket? • Person with the least tickets? • Person with least high priority tickets? • How to know which agent is active? • Our system smartly assigns tickets to one of active agents • Trying to find balance AGENTASSIGNMENT
  • 28.
    Future Work • Dockerizeeverything!!! • Automatic cancelation of orders based on tickets • Connection with ERP system • Automatic responses (or at least semi automatic) • DEEP THOUGHT *Hitchhikers guide to the galaxy FUTUREWORK
  • 29.
    THANK YOU. Automation isdriving the decline of banal and repetitive tasks. - Amber Rudd