H2O.ai Case Studies Predictive Model Factory

Edit This Case Study Record

	Predictive Model Factory H2O.ai

Predictive Model Factory

H2O.ai

Technology Category	Analytics & Modeling - Big Data Analytics Analytics & Modeling - Predictive Analytics
Applicable Industries	Telecommunications
Applicable Functions	Business Operation Sales & Marketing
Use Cases	Demand Planning & Forecasting Predictive Maintenance
Services	Data Science Services
Challenge	Cisco, a multinational technology company, faced challenges in building models to deliver accurate predictions about customer propensity to buy across its extensive product portfolio. The company was struggling with speed and scalability challenges associated with analyzing an exploding amount of information about buying patterns. The company had to recreate all its predictive models from scratch every quarter, a process that took more than four weeks. To avoid even longer processing times, models were trained on relatively small samples that were rarely larger than 100,000 cases. The company was limited to standard techniques and was unable to test competing algorithms such as ensembles, grid search, and deep learning. Read More
About Customer	Cisco is a multinational technology company that develops, manufactures, and sells networking hardware, software, telecommunications equipment, and other high-technology services and products. The company has a wide variety of networking equipment ranging from routers to switches. More recently, Cisco has also started to sell a variety of analytics and software solutions such as data center analytics and automation software. The company has a 20-person advanced analytics team that deploys a set of propensity to buy (P2B) models every quarter, which predict whether certain companies will buy certain products within a given timeframe. These predictions are used by marketing and sales teams to focus on their highest potential revenue opportunities. Read More
Solution	Cisco deployed H2O's pre-built ready-to-use algorithms to build models for accurate predictions. The company streamlined its prediction factory to a much simpler input controlled using R. Cisco leveraged H2O's in-memory compute engine to minimize the need for expensive storage resources and incorporated a greater amount of up-to-date customer buying information. The company used H2O to make better and faster predictions through sophisticated, ready-to-use algorithms and processing power to analyze bigger datasets, more variables, and more models. With H2O, new buying patterns were incorporated into models immediately. Scores were published sooner, leaving more time for campaign planning and execution. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Big Data Analytics

Analytics & Modeling - Predictive Analytics

Applicable Industries

Telecommunications

Applicable Functions

Business Operation

Sales & Marketing

Use Cases

Demand Planning & Forecasting

Predictive Maintenance

Services

Data Science Services

Challenge

Cisco, a multinational technology company, faced challenges in building models to deliver accurate predictions about customer propensity to buy across its extensive product portfolio. The company was struggling with speed and scalability challenges associated with analyzing an exploding amount of information about buying patterns. The company had to recreate all its predictive models from scratch every quarter, a process that took more than four weeks. To avoid even longer processing times, models were trained on relatively small samples that were rarely larger than 100,000 cases. The company was limited to standard techniques and was unable to test competing algorithms such as ensembles, grid search, and deep learning.

About Customer

Cisco is a multinational technology company that develops, manufactures, and sells networking hardware, software, telecommunications equipment, and other high-technology services and products. The company has a wide variety of networking equipment ranging from routers to switches. More recently, Cisco has also started to sell a variety of analytics and software solutions such as data center analytics and automation software. The company has a 20-person advanced analytics team that deploys a set of propensity to buy (P2B) models every quarter, which predict whether certain companies will buy certain products within a given timeframe. These predictions are used by marketing and sales teams to focus on their highest potential revenue opportunities.

Solution

Cisco deployed H2O's pre-built ready-to-use algorithms to build models for accurate predictions. The company streamlined its prediction factory to a much simpler input controlled using R. Cisco leveraged H2O's in-memory compute engine to minimize the need for expensive storage resources and incorporated a greater amount of up-to-date customer buying information. The company used H2O to make better and faster predictions through sophisticated, ready-to-use algorithms and processing power to analyze bigger datasets, more variables, and more models. With H2O, new buying patterns were incorporated into models immediately. Scores were published sooner, leaving more time for campaign planning and execution.

Impact #1	A dramatic reduction in processing time from more than a month to two days - despite a dramatically larger dataset.
Impact #2	The ability to analyze the entire set of customer data, rather than just a small sample - delivering far greater accuracy.
Impact #3	Immediate incorporation of new buying data with no need to prepare models in advance.

Impact #1

A dramatic reduction in processing time from more than a month to two days - despite a dramatically larger dataset.

Impact #2

The ability to analyze the entire set of customer data, rather than just a small sample - delivering far greater accuracy.

Impact #3

Immediate incorporation of new buying data with no need to prepare models in advance.

Benefit #1	Processing time reduced from over a month to two days, a 15x increase in speed.
Benefit #2	The ability to train models using data from tens of millions, rather than hundreds of thousands of cases from its database of 160 million customers.

Benefit #1

Processing time reduced from over a month to two days, a 15x increase in speed.

Benefit #2

The ability to train models using data from tens of millions, rather than hundreds of thousands of cases from its database of 160 million customers.

Download PDF Version

Overview

Predictive Model Factory

Operational Impact

Quantitative Benefit