reifier product brief
TRANSCRIPT
© Nube Technologies
Better decisions through better data
© Nube Technologies
About Myself and Nube- AI and Big data- Nube Products - Reifier, Crux and HIHO - IIT Delhi, 98.- International Speaker, Program Committee
Strata Hadoop World Singapore - Cofounder from IIT Kanpur, 97
© Nube Technologies
Customer Feedback
Before Reifer we had to use a lot of manual efforts to identify potential duplicates in customer data, now the system can learn patterns and find duplicates for us
intelligently. It’s a breakthrough to a long-standing issue of our businesses.”
- Mr. Dave Chan, Regional Director Business Intelligence, UBM Asia
© Nube Technologies
Reifier Coverage
© Nube Technologies
Reifier - Coverage
© Nube Technologies
Part of MapR App Gallery, Partner with Cloudera, AWS and HortonWorks
Reifier Industry Validation
© Nube Technologies
Business Data is spread across many systemsDiscovering information a challenge - which are the entities
whom we need to address?Consolidating information a challenge - not sure if the data is
tied back to a single entityEnhancing data a challenge - are these new records genuine
or do they already exist?
Business Challenges
© Nube Technologies
The problem - lake or swamp?According to Gartner, businesses lose upto 25% of potential revenue due to lack of multichannel view of data. 67% data scientists say cleaning, organizing and linking data is their most time consuming task, and 52.3% cite poor data quality as their biggest challenge.
© Nube Technologies
50 shades of data
Name Company Telephone
Dave C UBM Asia +91-8800541717
D Chan UBM 8800541717
Dave Chan UBM A
Dave UBM Asia 880-0054-1717
© Nube Technologies
Reifier advantage- Any variety of data (person name,
organization, address, telephone, mobiles, cameras..)
- Any language(english, chinese, japanese, thai..)
- Any scale(thousands to millions and billions)- Without any coding
© Nube Technologies
Name Company Telephone
Dave C UBM Asia +91-8800541717
D Chan UBM 8800541717
Dave Chan UBM A
Dave UBM Asia 880-0054-1717
Reifier Output - Multiple fields of different types
© Nube Technologies
Reifier Output - Word swapping with Different Cases, Leading and Trailing Spaces
Zyka's Kitchen 124 Queen Stshop 2 Cleveland
Zyka's Kitchen
Shop 2 124 Queen Street
Cleveland
CHATTHA RAJVINDER SINGH
SINGH CHATTHA RAJVINDER
© Nube Technologies
Reifier Output - Differences Sony Xperia M C1905 4GB Unlocked Smartphone YellowSony Xperia M C1905 4GB (Yellow) (IMPORTED)
Sony Xperia Z2 D6503 (Black) (IMPORTED)(IMPORTED) Sony Z2 D6503 (Black)Sony Z2 D6503 Black
Panasonic DMC-3D1 Lumix 12MP 4x Optical Zoom Panasonic Lumix DMC-3D1 12.1MP 4x Optical Zoom Digital Camera
© Nube Technologies
Reifier OutputSares Regis GroupSares-Regis Group
1800 Got Junk 83 Newmarket Road Lutwyche
1-800-GOT-JUNK 83 Newmarket
© Nube Technologies
Reifier Output
BA ONE SILKS AHAMED SHAFEEQ
18/5 EPPERY HIGH ROAD PERIMEET
B A ONE SILKS AHMED SHAFIQ 18/5 YEPPERY HIGH RD, PERIMEET
© Nube Technologies
Reifier Output - AbbreviationsAXA REIMAXA Real Estate Investment Managers
International Trade U 1 8 Ives Street
International Trade Unit 1 8 Ives Street
© Nube Technologies
Match various languages - thai, english, japanese, chinese..Baby Gap เสื้อยดืแขนสัน้ ลายจุดBaby Gap เสื้อยดืแขนสัน้ ลายขวาง
aera โซฟาเบด โดรา รุน่ FF01-A01-DR aera โซฟาเบด โดรา รุน่ FF01-A01-DR แพค็คู่ (Purple/Pink)
© Nube Technologies
Data volumes are highEach record has multiple dimensionsExact matches are rareComparing each record with every other is not possibleThere are many disparate systemsLanguages have unique issues
Technical Challenges for Matching
© Nube Technologies
Discovering and maintaining rules for data quality is extremely tough
Custom coding and domain specific logic makes maintenance a nightmare
No one size fits all, big custom implementations needed every time even after using existing tools
Technical Challenges for Matching
© Nube Technologies
Point and Shoot - Zero configLearns similarity definitions from dataNo hard coding of business rulesHighly scalable - runs on open source Apache SparkAdvanced Machine Learning algorithms pick most optimal
solutionDomain agnostic, can work with various kinds of dataUtilities to create labeled data available - just point it to the
data
Reifier Features
© Nube Technologies
Handles different languages - English, Chinese, JapaneseHighly accurate resultsAvailable as a library or as a private/public cloud
deploymentREST interfaceAJAX based web front endReal time as well as batch supportSupport and Documentation through web based support
portal http://reifier.freshdesk.com
Reifier Features
© Nube Technologies
Case Study - UBM Asia- Deduplication of marketing data- Combination of English, Chinese, Japanese
and other languages- Upto 1 million new records per week- Temp can do only about 800 records per day- AWS Hosted, yearly license- Reference customer
© Nube Technologies
Case Study - Government of India - Invited for data matching for intelligence
agencies- Reifier outperformed leading international
competition 2x on accuracy and >10x for speed
- Matched 40million records
© Nube Technologies
A local search company lists millions of regional businesses. They also source business information from third parties. Reifier helps the search company compare their existing listings with potential listings from third parties, and keeps their directory up to date and free from duplicate data.
Case Study - Directory Service
© Nube Technologies
A banking institution uses Reifier to run loan applications against credit listing data to ensure that they are not dealing with blacklisted individuals and corporates.
Case Study - BFSI
© Nube Technologies
Case Study - BFSIA leading insurance provider uses Reifier to prevent fraudulent claims. By creating a centralized consolidated data repository, the company reduces overexposure of an individual who has multiple policies. By matching records, Reifier also helps find out average policy per individual and household.
© Nube Technologies
A credit rating company utilizes Reifier to consolidate personal credit histories from different sources and provide accurate ratings to their customers.
Case Study - BFSI
© Nube Technologies
A telecom company offers various products and services and wants to cross sell to existing customers. Existing information is fuzzily matched for accurate customer segmentation and marketing.
Case Study - Cross Selling
© Nube Technologies
Case Study - RegulatoryRegulatory compliance of all kinds - including related to policies, taxes, privacy, anti terror, and anti money-laundering - require matching up data pulled from a variety of sources. With Reifier, organizations meet regulatory mandates with capabilities that support everything from simple deduplication of customer lists to matching data against government lists of suspected terrorists.
© Nube Technologies
A services company sources organization and people data from LinkedIn and Crunchbase and uses Reifier to match existing in house entities to identify leads.
Case Study - Lead Generation
© Nube Technologies
By consolidating vendor information from different geographies, source systems and channels, a retail operator gets a complete view of its supply chain and it able to garner better deals and discounts from its vendors. Reifier helps in cutting costs for the retailer.
Case Study - Retail Operations
© Nube Technologies
Case Study - TelecomUsing Reifier, telecom companies can detect delinquency patterns by identifying non paying customers who evade detection by enrolling with give similar sounding names and addresses with different formatting and spellings.
© Nube Technologies
Case Study - EcommerceMatching for competitive pricing and catalog enrichment
© Nube Technologies
Accept or create training data with marked duplicates
Identify similarity and indexing rules through Machine Learning
Group near similar records togetherMatch and predict similar records
Reifier Technology
© Nube Technologies
Reifier Architecture
© Nube Technologies
Reifier Workflow
Configure data
Reifier Interactive Learner
Linked Result
Have training data?Reifier Match
Yes
No
© Nube Technologies
Thanks for your time, please feel free to write to [email protected] for more details.
Thank You