One of the most common problems within the retail sector is pricing a product—not only initial pricing, but more importantly making the proper pricing decisions on an ongoing basis. Proper management of markdowns alone can contribute millions to a retailer’s bottom line. There are numerous similar products sitting on the shelves that are at different life stages and have complex interrelationships with other products and customers. Providing an optimal price of a SKU in order to extract maximum customer response is a challenge in itself. Virtually every retailer is running sales every week.

Usually each merchant looks at his or her business and decides what will be on sale. Yet the merchants typically do not know what customers will buy at full price and which will only buy on sale. If you could analyze the price sensitivity of each customer, you would find opportunities to significantly reduce your markdowns. Our Ergenomics Price Index is a unique method for modeling merchandise, customers and prices to help you index your customers’ price sensitivity. Some customers are so-called “cherry pickers” and will only buy an item when it is on sale. At the opposite end of the spectrum are non-price sensitive customers, who will just buy something because they want it or need it and do not care about the price.

Imagine the benefit of understanding price sensitivity at the individual customer level. What a powerful tool to use to reduce markdowns and to beat your competitors at the price game.  We calculate the price elasticity for products and accessories that have extremely high or extremely low elasticity along with reasonable business impact (sales volume, margins, or life stage). These accessories are picked for analysis. By using gross margins, we can come up with the best price change for such accessories.

Likewise, a basic market basket analysis can help find products that customers like to buy together. However, bundling needs to be evaluated for elasticity as well as likelihood of success before taking it to the customer. In order to increase the sale of some of the underperforming accessories, such accessories can be strategically bundled with highly elastic products. Similarly, a company will want to know the primary and secondary driver relationship qualities of each product (i.e., which product is the one that really makes people come to the stores). The gross margin of the bundle can be used for driving the price of the bundle.

In part 3, we’ll address how demand forecasting is leveraged to shorten the supply chain and improve profitability.

info@ergenomics.com

http://www.ergenomics.com

(612)245-4670

© ERGENOMICS 2009

It is no surprise that retail is an ever-changing and dynamic environment. With the economic and competitive landscape reshaping itself before our very eyes, retailers find themselves challenged to meet the customized demands of their customers, while still clinging to some sense of efficiency and scalability (and, profitability)- not an easy task by any means.

Companies need to be flexible and reactive so they can quickly respond to increasingly sophisticated customer demands. Businesses must be able to change their business models so they can collect real-time business information and drive the efficiency of their day-to-day operations.

Several critical challenges confront today’s retailer: price sensitivity, demand forecasting and inventory management, customer driven up-sell and cross-sell, multi-channel marketing, and fraud detection and loss prevention; just to name a few. Ergenomics believes in the use of enterprise wide analytics to create one common view of the enterprise which enables everyone across the organization to approach the business with the same set of numbers and data.

Our analytics approach starts with improving your customer knowledge. Retailing today is about making the process of getting the right products to the right customer at the right price at the right time a scientific, predictable routine. The days of “stack it high and watch it fly” are gone. This means making your organization as efficient and effective as possible.

As they say, “retailing is detailing,” and the devil is in the detail. That is where the Ergenomics’ Blueprint of Enterprise Analytics allows us to sift through massive amounts of data quickly and precisely to help you identify and predict selling opportunities. We leverage tools like SAS and SAP to help our PhD economists assess your customer information and help build you a Customer Performance Dashboard along with other reports to help you leverage the power of customer data. Our approach to retail analytics is robust and straightforward. Ergenomics deploys expertise (technological, analytical, and business line) that can hone in on opportunities with an organization to maximize their customer portfolio. All areas of concern can be addressed and optimized through our disciplined and rigorous execution.

Business Process > Data Analytics > Assess > Build > Optimize > Support > Train > Deliver

Understanding the current customer’s buying pattern, price sensitivity, interdependence of product lines to each other, and each SKU’s true and absolute profit contribution not only produces immediate results, but can be modeled forward to gain efficiencies in future operational and marketing decisions.

In part 2, we’ll address the topic of price sensitivity.

info@ergenomics.com

http://www.ergenomics.com

(612)245-4670

© ERGENOMICS 2009

by: Murat Ergen, ForecastWare.com

Forecasting helps to obtain a good comprehension of the observed data and accurate future predictions based on this comprehension. The main goal, however, is to assist executives with decisive information they absolutely need to make the best possible decisions. Acting on these recommendations can significantly aid in solving problems, gaining new opportunities, and ultimately better business management. Examples of possible uses of forecasting are to reach corporate goals, to plan external economic and competitor impacts, to improve inventory management, to improve customer service, and to increase profit margins.

Key elements in forecasting are Team and Framework. In this article, characteristics of both are mentioned.

A successful forecasting system starts with forming a good team. Essential team members are Business Analyst, Data Analyst, Project Manager, Statistician, and Solution Architect.  Roles and responsibilities each member contributes to organizational direction. Business Analyst makes sure credibility of the business information through careful research. Data Analyst automates historical file extracts, and optimizes the process time and accuracy. Project Manager has a unique position in forecasting projects, because of responsibility of asking details about the system and its sponsors. Statistician is responsible to find what is unknown, the forecasts, by studying the actual numbers and applying internal or external factors. Solution Architect works with system results as well as other available data to create a visualization tool for business leaders to make data driven decisions. With this team in place the following benefits could be expected; collecting business owner needs, and changes in the business, business approval of pre-published numbers, increased timeliness of business decisions, what-if scenarios implementation, short timeline delivery, easy to use custom solution interface, integration of major economic indicators and competitors market share, unnoticed real trends discovery, maximized profit margins opportunity, strategic business portfolio creation, on the spot tactical recommendations, centralized one version of truth, collaboration with other official numbers, automated step by step process, mitigation of known and unknown risks, and institutionalized ongoing maintenance.

The Framework for the forecasting system should include the following phases; Data Gathering, Information Gathering, Modeling, Reporting, and Recommendations. In the data gathering phase, historical data is extracted to be studied in order to gather historical data at the most granular level possible, input missing data points and attributes, structure hierarchy levels, and determine the business focus hierarchy level accuracy is tested. Information gathering phase follows what collected data is to note internal business circumstances, implement structural brake notifications, and detect anomalies and outliers. Modeling phase is where normalizing and transformation of data is taken in to account and studying the relationship between observed data and economic and competitor indicators. It this phase also models are estimated, validated, tested and selected to create forecasts. Reporting phase of the framework helps in both forecasts quality and applicable information selection such as static accuracy testing, dynamic best and worst performance analysis. Recommendation phase where Return On Investment are clearly observed because this phase tells business users where the potential goal gaps are, what resources to be added in business operation, and simply brings various departments to one table to list actionable items.

Some of the items need more emphasis;

• - Such as experienced statistician who has industry knowledge and built dynamic forecasting engines previously
• - The systems results needs to be reviewed regularly, this review includes business expected numbers and model numbers accuracy testing, what is working and what needs to be improved, model attributes
• - Constant Business and Forecasting Team communications
• - Selecting forecast engine tool for the corporate need and building a customized visualization tool for result comparisons such as actual to actual, goal to actual, forecast to goal

In conclusion, this article is about what is essential for a successful forecasting project. It is teamwork with applied framework. As long as these two are in place building, adjusting and maintenance of forecasts for the whole organization is an easy task. ForecastWare.com is built on this fundamental approach.

http://www.ForecastWare.com