Use Cases

Jump to Industry:

How best to tailor stock levels for revenue optimization?

Case Study
Topic:Demand Prediction

Retailers lose more than $1 trillion a year from inadequate inventory control for out-of-stock and overstocked merchandise, according to an IHL Group research report.

An ecommerce retail intelligence provider was looking to predict future demand for specific products that its customers sell.

Personalization for Retailers of Any Size

Use Case
Topic:Product Recommendation

Personalization cannot remain the purview of retail giants. Retailers of any size need the ability to build recommendation models. AutoML gives them the capabilities to build custom models based on their own data and their own business goals. Optimizing the right offer for each customer enables companies to increase sales and customer loyalty.

Using Firefly Lab to handle growing demand for machine learning models in cybersecurity

Case Study
Topic:Anomaly Detection

Cybersecurity is a $150 billion market worldwide and growing rapidly. It is an ever-changing environment where attackers and defenders are in a constant race to get ahead of one other.

A cybersecurity company with a sophisticated technology edge is successful in getting ahead of attackers by applying anomaly detection to identify active attacks on network traffic. However, with success, comes the challenge of how to rapidly scale data science productivity to match company growth. Can it be done without compromising machine learning model performance?

New life for rule-based analytics system with Machine Learning

Case Study
Industry:Homeland Security
Topic:Anomaly Detection

The rapidly-growing global market for mass transit security systems already exceeds $10 billion a year. Increasing instances of violence and rising awareness about mass transit security systems led to its growth. Mass transit security systems gather real-time data on the performance of trains and increase safety with sensors installed near railway tracks. These security systems are used to prevent train collisions and derailments and stop unauthorized access to fenced-off areas.

Fix before you Fail

Use Case
Industry:Manufacturing and facilities
Topic:Predictive Maintenance

Predictive maintenance is mission critical to shielding commercial and industrial facilities from tremendous risk and cost. Accurate modelling discovers slight changes in asset operations and alerts to oncoming malfunctions. With the speed of AutoML in creating as many models as needed, companies directly address any number of scenarios that impact predictive maintenance. A dedicated model built for each set of specific conditions significantly enhances precision. The results: Companies maximize equipment uptime and make cost-efficient maintenance decisions.

Retain customers quicker than they can leave

Use Case
Industry:Banking and Telco
Topic:Customer Churn

Churn is a constantly moving target. By the time companies assess which customers will churn (discontinue a service or stop buying products) in a given time frame, different factors will have influenced customer behavior going forward. The rapid-fire, multiple-model approach of Firefly enables businesses to move more quickly than their customers can. When businesses can automatically-generated models for any time frame or customer profile they desire, they meet customer needs and deter attrition to enjoy massive cost savings.

Credit scoring that’s both spot on and crystal clear

Use Case
Topic:Credit Risk

The flexibility provided by an AutoML, which swiftly trains and builds as many models as you want, is much better suited to the nonlinear relationships between explanatory variables and default risk. Unlimited capacity afforded by Firefly gives you access to the broadest set of variables you desire to significantly improve accuracy. Transparency and explainability provided by Firefly Lab’s full reporting provide precisely what is needed to comprehend how decisions are made.

Keeping Customers Content

Kaggle Challenge
Topic:Customer Satisfaction

Dataset: Santander Customer Satisfaction dataset

Goal: Predict dissatisfied customers without detailed features and background.

Dataset: Anonymized dataset with 370 features for 76,020 customers

Making sense of feature overload to optimize business processes

Kaggle Challenge
Topic:Reliability Prediction

Dataset: Mercedes-Benz Greener Manufacturing dataset

Goal: Predict the length of time it takes for each configuration of car to pass testing.

Dataset complexity: Small dataset with the curse of dimensionality: training data of 4,209 rows with a relatively large number of features, 377