How to predict if your best employees are about to walk out the door

SAS^® Human Capital Management helps Banca Carige to retain employees and save costs

Banca Carige, one of the oldest banks in Italy, wanted a way to identify which of their employees were most likely to resign, because these people take their valuable knowledge and skills along with them when they go – assets that are expensive and time-consuming to quantify and replace.

Discovering the underlying reasons that prompt employees to leave and then designing effective strategies that encourage them to stay is the critical success factor for the bank. With the predictive modelling capabilities of SAS Human Capital Management, Banca Carige is able to identify the key employees most likely to leave and to act upon the information to retain them.

Managing human capital assets
Banca Carige believes that human capital assets are very important, as employee costs exceed 44 percent of all organizational expenses. There are the tangible employee costs such as replacement, training and lost productivity, and intangible costs such as loss of intellectual capital and low employee morale.

"The current trend in banking throughout Italy is definitely upward growth, and Banca Carige has been no exception," says Udo Cordara, Employees Development Director at Banca Carige. "The bank has recently hired a significant number of new employees as the business in its various units – such as commercial sales, and private, retail and corporate banking – has grown. Banca Carige currently has approximately 5,000 employees, nearly double the number of employees just four years ago. The increased hiring trend has made it necessary for the bank's HR Department to evaluate all employees' particular skill sets and competencies.

"The new generation of employees at Banca Carige is very young, and one problem that the HR Department faces is that, because the banking market in Italy is growing so quickly, there are ever more career possibilities and opportunities, and salaries are increasing. It is just as important for us to work to retain our employees as it is for us to retain our customers. I have been active in introducing the concept of employee relationship management. The internal customer is very important.

"Our ultimate goal right now is to predict if our best employees are about to walk out of the door. The impetus is simply to save money – it is expensive to hire and train new people and cheaper to retain those we already have. We wanted a retention model for predictive modelling to anticipate, forecast and analyze information and trends, proactively plan for the future and realize cost reductions."

Accessing data and providing transparency
The HR Department realized that they needed a unique HR information system. They were dealing with unrelated, disparate systems – one system for payroll, one for management, one for employee profiles and so on – and they needed a solution that could access information from all these sources. They had the problem of having a lot of data, but no actionable information.

"We absolutely had to solve the pain of dispersed HR data," says Cordara. "When a top manager asked me specific questions such as: 'How many people have resigned from the retail department?' or 'What are the personnel costs in the commercial sales department?' I could answer, but only after working hard for many days extracting the relevant information from systems A, B, C and D, and so on, and then organizing it all in Excel to produce a statistical report.

"We needed a business intelligence solution that could provide answers to such questions more quickly – we knew the appropriate data was there and we knew where it was, but we needed an easier way to access it, analyze it and give it to management for them to use, faster. Another issue is that there is a new culture and mission at the bank for internal knowledge management to be more transparent, and this is also to be achieved by distributing and transferring the knowledge from the business units to the top management."

Choosing SAS
Banca Carige wanted a software vendor that could provide them with one version of the truth. During the software selection process, they looked at many different vendors who said they offered business intelligence and reporting, but the bank chose the SAS Human Capital Management solution because it was fast and easy to implement, and the human capital data model for the HR Department had more dashboard and OLAP capabilities, better analysis and faster query and reporting. Banca Carige had been using SAS solutions in several different departments for many years, and therefore the HR Department was confident that SAS could meet their needs.

"The knowledge of SAS personnel was important because they spoke the language of the bank's HR people and understood the issues and concerns of the department," says Cordara. "During the sales presentation, I asked SAS people a lot of detailed questions and they knew the answers right away. The bank has a good relationship with SAS as a company.

"Implementing the retention model was our first mission – to divide the people into segments with targets, just as we do with our customer relationship management program. We divided people into communities of key players and then modelled segments of the population. There are targets and models in areas such as compensation and education, for example."

Implementing the retention model
"The Human Capital Management project started two years ago, the first phase was completed one year ago, and in early 2004 we started the retention model project," continues Cordara. "Using SAS, the bank created a state-of-the-art employee data warehouse that contains employees' identifying and professional data, with such parameters as: age, gender, salary, job role, education and formation level. With this information we can create new standard and ad hoc reports and produce "what-if" analysis and salary simulations.

"The retention model is a natural extension of the SAS Human Capital Management solution, as it incorporates SAS' core competencies of data warehousing, predictive analysis and reporting, and provides a clear competitive advantage." It uses data already in the data warehouse, and uses results to enrich the warehouse. It is based on a defined procedure and uses SAS Enterprise Miner to: analyze the factors associated with voluntary separations, build a model to predict the likelihood of an employee voluntarily separating, score all employees based on the model and deliver standard and customized reports based on the results of the model.

"Some results that the retention model provides are that code is generated to calculate information about model interpretation, risk segments are calculated and segmented into low/moderate/high and the results flow back into the data warehouse for reporting and analysis."

The kinds of questions that they can easily answer now include such things as:

• Which employees are at the highest risk of voluntarily leaving the organization?
• What reasons do employees have for wanting to leave?
• Which reasons have the most statistical significance to why employees leave?
• What is the profile of employees most likely to leave?
• How is the risk distributed throughout the organization? And
• Are the top performers at risk of leaving or actually leaving?

Speaking the language of business
"The Human Capital Management retention model first ran in January 2004, and by March the employee who was designated as ninth most likely to leave had resigned," says Cordara. "It has short implementation times and low cost and the model can be refined to improve accuracy, increase history depth and increase employee attributes.

"The retention model shows us that turnover currently stands at three to four percent, and that the rate is low because the people identify with the culture, the brand and the corporation, and this is very important because it shows buy-in with the employee relationship management concept. While low turnover is crucial, it is just as important to keep turnover from increasing, and the retention model from SAS helps with both issues.

"Using SAS, I can present the retention model results to top management quickly, and they are so enthusiastic that they want to extend the use of the retention model even further. We now have high management buy-in and a standard best practice in this situation, thanks to the capabilities provided by the SAS Human Capital Management solution. We know there are good resources in SAS – good people, good solutions and good technologies. The SAS solutions speak the language of our business."

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Copyright © SAS Institute Inc. All Rights Reserved.