Brian Keith is a Director at GlassRatner. He also joined the Atlanta office as a Data Scientist in 2022, bringing four years of experience in the pulp and paper and mining industries, with a focus on process optimization, modeling, and the development of Python based analytics tools. At GlassRatner, Mr. Keith manages the firm’s big data engagements, guides advanced analytics, and develops algorithms for complex datasets.
Due to the broad areas where his expertise can support client needs, Mr. Keith has worked on a wide range of matters. His notable experience includes developing sampling methodologies and algorithms for classification of warranty replacements in a class action lawsuit involving a large retailer. His work created a reliable sampling methodology to critique an opposing expert’s damages claims and strengthened the ability to match damaged transactions.
Mr. Keith has also supported multiple cases for some of the largest commercial shipping companies in the world, including damage disputes related to package weights and billing charges. His work included shipment data analysis to determine the validity of disputes and classification algorithm development to assess damages caused by under manifested package weights.
His experience further includes data breach matters, such as a case involving over 51 billion datapoints of PHI and PII released by a healthcare billing company. Mr. Keith reconstructed databases, consolidated data, and analyzed exposures to determine class membership and assess damages related to the breach.
He has assisted in damage assessments for a large payment authentication company accused of unlawfully storing and selling user financial data, involving hundreds of millions of records. Mr. Keith has also worked on fraud investigations, including analysis of fake treasury trades, database modifications, and reconciliation of clearinghouse and unmatched trades to determine net exposure.
Additional engagements include the development of various statistical sampling methods involving monetary unit sampling for a national health insurance provider; breach of contract disputes for a large retailer of aftermarket car parts, where Mr. Keith created flow through sales chain algorithms; and modeling of over one billion dollars’ worth of receivables.
Mr. Keith is fluent in Python, R, and SQL, with working knowledge of JavaScript, HTML, and VBA. His experience includes web scraping, computer vision, and machine learning for complex data challenges. He holds a Bachelor of Science in Chemical Engineering from Auburn University and a Master of Science in Data Analytics from Georgia Tech.
- Database Management
- Statistical Modeling
- Root Cause Analysis
- Time Series Forecasting
- Data Extraction
- Data Aggregation
- Data Visualization
- Expert services related to sampling methodologies and algorithm development for classification of warranty replacements in a class action lawsuit related to a large retailer, including development of a reliable sampling methodology to critique opposing expert damages claims and match damaged transactions
- Multiple cases for one of the largest commercial shipping companies in the world related to damage disputes regarding package weights and billing charges, including shipment data analysis to determine validity of disputes and development of classification algorithms to assess damages due to under manifested package weights
- Multiple data breach cases, including one pertaining to a data breach for a healthcare billing company involving over 51 billion datapoints related to PHI and PII, including reconstruction and consolidation of databases and analysis to determine class membership and information exposure
- Assisting to determine damages related to a large payment authentication company accused of unlawful storage and selling of user financial data without consent, involving hundreds of millions of records
- Fraud investigation related to fake trades on treasury bonds, including creation and modification of data structures to determine net exposure created by fake trades
- Development of statistical sampling methods involving monetary unit sampling to determine damages associated with lost profits for a medical billing dispute and claim sampling for a national health insurance provider
- Breach of contract disputes related to a large retailer of aftermarket car parts, including development of algorithms to flow transactions through sales chains and perform statistical analysis to prove plaintiff claims
- Modeling and upkeep of data related to over $1 billion worth of cumulatively purchased receivables for GlassRatner