The client needed to identify the geolocation data provider - out of dozens available - that best aided their investment strategy.
- Different preprocessing (data capture, cleansing, metric creation) logic used by vendors
- Lack of standardized evaluation criteria
- Lack of data acquisition, load and process governance/oversight
- We developed a set of evaluation metrics (e.g., data consistency, KPI correlations) relevant to the client
- We designed a vendor questionnaire that allowed us to effectively screen the vendors prior to data capture
- We decoded each vendors’ preprocessing algorithms, applied logic to bring consistency for evaluation, and developed analytics modules that evaluate a dataset in 1-2 days
- Lastly, we concisely synthesized information for the client and recommended finalists based on their needs
Fulcrum’s methodical approach and data audit framework evaluated multiple data sources through a consistent lens, quickly and effectively.
A regional bank’s Human Resources (HR) group was seeking a solution to incorporate market and competitive data to improve personnel evaluation and optimize resource planning.
- We integrated external data (e.g., publicly available competitor data, footprint demographics, etc.) with internal data (e.g., staff experience, branch performance, etc.) and developed new data elements on branch-level market share
- We created a deposit growth segmentation to benchmark branch growth and market penetration, controlling as many factors as available, excluding manager talent
- Lastly, we performed branch performance forecasting for each segment
Fulcrum streamlined the ability to identify exceptional managers, which impacted compensation formulas and recruiting efforts, and also enabled optimized resource planning through forecasting
The client needed help flagging fraudulent medical insurance claims. The goal was to:
- Determine logic to flag suspicious behavior and identify providers of interest
- Leverage billing data to analyze suspicious providers
- We performed fuzzy matching to link multiple claim records to the same provider(s)
- We used geocoding to create physical distance calculations between providers and between providers and claimants
- We applied statistical methods (e.g., logistic ridge regression with sparse matrices, T-Score calculation, bootstrapping, etc.) to billing data to build propensity scoring models to rule claims as valid or invalid
- Based on our modeling results, we created the fraud flagging logic to identify suspicious behavior and providers of interest
- The team collaborated with the investigative unit, billing unit, and legal unit to create a provider fraud action plan
Fulcrum's data preparation procedures and predictive analytical models provided the quantitative basis for the provider fraud action plan.
Retailers of all kinds want to understand the attractiveness of their local markets and how they fare against market competition:
- Public data is available to answer these questions - but come from multiple sources. Some are extremely large and most have quality issues
- Manual analysis for any given store, branch, or collection of local markets is time consuming and prone to error
- Exploratory analysis requires technical expertise and access to data and computing resources - business users can't easily answer "what if" questions
- Built automated process to retrieve, clean, and combine dozens of distinct public datasets to create a master database of local market performance & demographic data for the entire US across 8 years
- Automated creation of detailed reports for any retailer. Reduced time to create a tailored presentation from weeks to minutes
- Built an interactive application to allow business users to explore the data and create custom charts to answer questions related to company performance
Fulcrum’s web application allows instant visualization of massive public datasets
To perform exploratory analysis on the impact of IoT devices on homeowners insurance claims, the client sought to merge claim data with IoT information (provided by a third party).
The challenge was third party and the client not being able to share data across systems for data security reasons.
- Fulcrum facilitated IoT analytics by acting as a third party to join proprietary information between the two companies
- We collected sensitive data in isolation in our highly fortified security infrastructure, and performed matching at the home address level
- Then we provided an anonymized joined data set to the client and developed a framework to repeatedly supply the data transformation between the two companies
Fulcrum quickly and securely provided the neutral data matching required to support various insight needs across the organization.
The client was seeking a streamlined method to organize their disparate data sources into a single location to start generating business insights. Some of their challenges included:
- A massive amount of disjointed information including internal and external data
- The lack of a unified view of the customer because the source systems are managed by different siloed teams
- The internal IT team was backlogged, and analysts needed support testing the latest big data tools
The client partnered with Fulcrum to utilize our Agile Analytics Lab to experiment with big data solutions
- We created reusable data processing pipelines to allow easy data loading into Hadoop and data preparation for analysis
- After establishing the central repository, we then cubed the data using Hive and Spark for fast querying of metrics
- Output tables are stored in HBase and Impala is used for queries to gain rapid response while Tableau is utilized for dashboard reporting
Fulcrum’s lab enables a holistic view of the data to unlock insights and allows rapid testing of various open source tools. Our data experts guide the process allowing the clients to modernize their analytics team.
The client needed to accomplish faster and more accurate decisions in making personalized offers. Fulcrum applied its experience in digital coupon operations to solve the business problem.
The client partnered with Fulcrum to utilize our hosted computing platform, Digital Fusion.
- Digital Fusion collected data across all channels and sources (POS, display ad, email campaign, web traffic) and created hundreds of micro-segments of customers with similar buying behavior
- The platform deployed stochastic frontier models for each segment to identify winnable shares for each product category
- Then Digital Fusion computed the optimal personalized offers based on purchase, coupon redemption, and digital behavior data
Fulcrum's unification of behavioral and marketing data with predictive models produced granular personalized offers to drive more trips, bigger baskets, and higher margins.