H2O.ai > 实例探究 > Predictive Model Factory

Predictive Model Factory

公司规模

1,000+

地区

America

国家

United States

产品

H2O's pre-built ready-to-use algorithms
H2O's in-memory compute engine
Cisco's propensity to buy (P2B) models

技术栈

实施规模

Enterprise-wide Deployment

影响指标

Cost Savings
Productivity Improvements

技术

分析与建模 - 大数据分析
分析与建模 - 预测分析

适用行业

电信

适用功能

商业运营
销售与市场营销

用例

需求计划与预测
预测性维护

服务

数据科学服务

关于客户

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.

登录后查看完整内容

挑战

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.

登录后查看完整内容

解决方案

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.

登录后查看完整内容

运营影响

A dramatic reduction in processing time from more than a month to two days - despite a dramatically larger dataset.
The ability to analyze the entire set of customer data, rather than just a small sample - delivering far greater accuracy.
Immediate incorporation of new buying data with no need to prepare models in advance.
The power to deploy of advanced machine learning algorithms (including GBM and deep learning) - rather than simple decision trees - for more accurate results.

登录后查看完整内容

数量效益

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

登录后查看完整内容