Subscribe to DSC Newsletter

Dr. Vincent Granville is a visionary data scientist with 15 years of data mining, big data, text mining, predictive modeling, business analytics, quantitative analysis and digital analytics experience. Vincent is widely recognized as the leading expert in scoring technology, fraud detection and web traffic optimization. Over the last ten years, he has worked in real-time credit card fraud detection with Visa, advertising mix optimization with CNET, A/B testing with LowerMyBills, online user experience with Wells Fargo, search intelligence with InfoSpace, automated bidding with eBay, data mining with Microsoft, click fraud detection with major search engines and large advertising clients, as well as statistical litigation.


Vincent was formerly Chief Science Officer at Authenticlick. Most recently, he successfully launched AnalyticBridge, the largest social network for analytic professionals, with 45,000 subscribers. Vincent is a former post-doctorate of Cambridge University and the National Institute of Statistical Sciences. He was among the finalists at the Wharton School Business Plan Competition and at the Belgian Mathematical Olympiads. Vincent has published 40 papers in statistical journals and is an invited speaker at international conferences. He also developed a new data mining technology known as hidden decision trees, owns multiple patents, published the first data science book, and raised $6MM in start-up funding.

+ Email: [email protected]

Specialties

data mining, six sigma, web analytics, text mining, pattern recognition, crm, sas, predictive modeling, splus, jmp, perl, web mining, machine learning, knowledge discovery, ai, sql, large data sets, data analysis, survey analysis, customer profiling, churn, user retention, search engine, query intelligence, credit card fraud, click fraud, scorecards, clustering, decision trees, logistic regression, advertising mix optimization, pareto analysis, business intelligence, design of experiments

Experience

July 2012 – Present (4 months)

Leading online career community for data science, big data and all business analytic positions. Growth hacker. Manage the bi-weekly newsletter sent to 80,000 subscribers, featuring career articles and the most recent advertised positions, reaching more analytic practitioners than all our competitors combined - including KDNuggets, SmartDataCollective, INFORMS, Data-Informed, American Statistical Association, Digital Analytics Association, etc. Research analyst, editor, co-founder.

I also provide consulting on traffic quality, click fraud and click scoring for meta job boards. Provide scalable, simple, customized and robust solutions that outperform traditional scoring technology, with superior ROI and fewer false positives / false negatives. Reverse-engineered solutions offered by previous vendor.

January 2012 – Present (10 months)

Leading data science, visualization, data integration and analytics community hub. Growth hacker. Data scientist, developer, author, blogger, speaker, professor, consultant, patent inventor, recruiter, community manager, co-founder, CFO, product and business development. Social network, fraud detection, business analytics, digital and email marketing expert.

Internet industry

February 2008 – Present (4 years 9 months) Greater Seattle Area

Leading social network for data science professionals (80,000 subscribers). 

KEY ACHIEVEMENTS:

Vincent Granville, along with Analyticbridge, was named as a top 20 Big Data influencers by the Forbes magazine, in 2012.

Publication of the Data Science ebook, (10,000 downloads): http://bit.ly/oB0zxn 

ANALYTIC COMMUNITY:

Responsible for computational marketing, traffic growth, and strategic partnerships. Increased revenue by 100% from 2011 to 2012. Advertisers include EMC/Greenplum, FICO, SAS, StatSoft, Gartner, Northwestern University, Angoss, Strata, DataStax, Elsevier, Lavastorm, recruiters, small companies and major ad agencies. 

CONSULTING: 

• Developed Internet traffic scoring platform for ad networks, advertisers and publishers (rule engine, site scoring, keyword scoring, lift measurement, linkage analysis). Clients include eBay, Click Forensics, Cars.com, Turn.com, Microsoft, Looksmart.
• Designed the architecture for one of the first analytics 3.0. online platforms: all-purpose scoring, with on-demand, SaaS, API services. Currently under implementation.
• Engineered the most popular real time analytics news feed: responsible for architecture (super-cluster topology), implementation (automated content selection) and distribution. 
• Identified major Botnets generating more than 10MM per year in fraudulent transactions. 
• Search engine analytics: prediction of keyword conversion for keywords with little or no historical data, increased lift by 20%. 
• Web crawling and text mining techniques to score referral domains, generate keyword taxonomies, and assess commercial value of bid keywords.
• Collaborative filtering, social network analytics.
• Developed new hybrid statistical and data mining technique known as hidden decision trees and hidden forests.
• Invited speaker: Predictive Analytics World, SAS International Data Mining Conference.

Vincent has 2 recommendations (1 co-worker, 1 client) including:

Public Company; 11-50 employees; LOOK; Internet industry

April 2010 – March 2012 (2 years)

Keyword and search analytics using machine learning and pattern recognition:

• Created the list of top commercial keywords that account for 85% of all advertising revenue on Google.
• Implemented and programmed the Google AdWords API to automatically find millions of new high value / high volume keywords for advertising campaigns (Perl, SOAP, XML)
• Taxonomy improvement. 
• Click fraud detection (click jacking and Botnet detection). 
• Web site scoring, with scores used to predict chances of conversion or sales, using hidden decision trees / Naïve Bayes and web crawling. 
• Automated bidding for advertiser campaigns based either on keyword or category (run-of-site) bidding.
• Reverse engineering of keyword pricing algorithms in the context of pay-per-click arbitrage.
• Creation of multi-million bid keyword lists using extensive web crawling. Identification of metrics to measure the quality of each list (yield or coverage, volume, and keyword average financial value). 


LookSmart is an online search advertising network solutions company that provides performance solutions for online search advertisers and online publishers. LookSmart offers advertisers targeted, pay-per-click (PPC) search advertising and contextual search advertising via its Advertiser Networks; and an Ad Center platform for customizable private-label advertiser solutions for online publishers. LookSmart is based in San Francisco, California. For more information, visit www.looksmart.com or call 415-348-7500.

Vincent has 1 recommendation (1 manager) including:

Privately Held; 11-50 employees; Internet industry

June 2006 – May 2008 (2 years)

Prototyped automated bidding and click scoring solutions for search engines, ad networks and advertisers. Worked with the engineering team to implement my algorithms. Design of Experiment. Score standardization. IP blacklist design and management. Patent-pending statistical technologies. Supported Sales and Production team. Presented at Ad-Tech and the American Statistical Association conferences. Helped win several deals against large competitors (including Fair Isaac). Identified major Botnet. Raised $1.5 MM (Venture Capital funding).

Vincent has 5 recommendations (4 co-workers, 1 client) including:

Public Company; 51-200 employees; INSP; Internet industry

January 2005 – June 2006 (1 year 6 months)

Click scoring technology, query intelligence, web analytics, business intelligence related to mobile search. Designed click fraud detection algorithms to process billions of clicks. Created rule selection and rule discovery system for fraud detection, based on machine learning (unsupervised clustering), design of experiments, robust cross validation and linkage with external data sources (Google search results) to discover additional fraud patterns. Enhanced keyword taxonomies using data driven algorithms to detect keyword associations. Defined and tested metrics for keyword correlations. Developed multi-threaded web crawler to feed text mining algorithms with rich, targeted data sources related to local search and / or yellow pages.

Keywords: data mining, text mining, query intelligence, keyword taxonomy, clustering algorithms, impression fraud, click fraud detection, click quality, search engine, web analytics, web crawler, design of experiments

Vincent has 3 recommendations (2 managers, 1 co-worker) including:

  • 1st Greg Sundberg, Senior Director, Business Intelligence, Infospace
  • 1st Sridhar Koneru, Senior Software Development Engineer, Infospace Inc

May 2002 – December 2004 (2 years 8 months)

• Real time credit card fraud detection, with Visa: improved speed of feature selection algorithm by a factor 200. 
• Online user behavior analysis with Wells Fargo: significantly reduced churn and improved site navigation. 
• LowerMyBills.com – 3 months contract, saved $80K by improving A/B testing methodology. 
• Statistical litigation. Automated copyright infringement detection. Web robot technology. Click fraud detection.

Vincent has 7 recommendations (2 co-workers, 3 clients, 2 partners) including:

Public Company; 10,001+ employees; WFC; Financial Services industry

June 2004 – November 2004 (6 months)

Analyse online traffic on B2B platform to optimize user experience. 

Keyword: data mining, web analytics, wells fargo, toad, oracle

Vincent has 2 recommendations (1 co-worker, 1 client) including:

Public Company; 5001-10,000 employees; V; Financial Services industry

February 2003 – May 2004 (1 year 4 months)

Develop proprietary feature selection system (200x faster than SAS Enterprise Miner) to detect first instances of fraud and horizontal (single ping) fraud in real time. Production of US zip code maps showing fraud simultaneously in the time, location, recency and volume dimensions. SAS, Perl, C, R, Splus.

Keywords: decision trees, SAS Enterprise Miner, fraud detection, data mining, web analytics

Public Company; 501-1000 employees; NBCI; Internet industry

2000 – 2002 (2 years)

Advertising mix optimization.

Public Company; 1001-5000 employees; CNET; Online Media industry

June 1996 – May 2002 (6 years)

Web analytics. CRM. Advertising reach and frequency: provided mathematical formula. Inventory forecasting. Price elasticity modeling. Web robot. Advertising mix optimization. Customer profiling. User retention, churn. Data Warehousing. Web traffic forecast (with automated alarm system to notify product managers of traffic abnormalities). Automating production of various reports (dashboard, quarterly reports for financial analysts). Perl, Sybase, SQL, SAS, CGI, C.

Keywords: web analytics, data mining, metrics, market research, market intelligence, business intelligence, competitive intelligence, SAS

July 1995 – June 1996 (1 year)

Environmental statistics. MCMC. Hierarchichal Bayesian models. Clustering. Storm modeling (time series, spatial processes). Hanford nuclear reservation: risk analysis (leakage) using space / time models. Simulation of bivariate exponential distributions.

Keywords: data mining, hierarchical clustering, Fortran, C, general linear models

Publications

  • Data Science eBook by Analyticbridge

    • Analyticbridge
    • October 4, 2011

    Our Data Science e-Book provides recipes, intriguing discussions and resources for data scientists and executives or decision makers. You don't need an advanced degree to understand the concepts. Most of the material is written in simple English, however it offers simple, better and patentable solutions to many modern business problems, especially about how to leverage big data.
    Emphasis is on providing high-level information that executives can easily understand, while being detailed enough so that data scientists can easily implement our proposed solutions. Unlike most other data science books, we do not favor any specific analytic method nor any particular programming language: we stay one level above practical implementations. But we do provide recommendations about which methods to use when necessary.
    Most of the material is original, and can be used to develop better systems, derive patents or write scientific articles. We also provide several rules of the thumbs and details about craftsmanship used to avoid traditional pitfalls when working with data sets. The book also contains interviews with analytic leaders, and material about what should be included in a business analytics curriculum, or about how to efficiently optimize a search to fill an analytic position.

Views: 217

Comment

You need to be a member of AnalyticBridge to add comments!

Join AnalyticBridge

On Data Science Central

© 2020   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service