Retail and online sellers are dealing with a complex environment of competition while at the same time managing their own multi-channel environment. These companies are already lean so there is not much room to cut costs. Therefore, the ability to increase revenue and improve margins through a more technologically advanced price optimization process can make a huge difference in their business. This is sometimes called dynamic pricing, defined as “Where businesses set flexible prices for products or services based on current market demands.”
The combination of accessible data, ability to experiment on line and new analytic technologies enable an innovative approach to pricing. However, there are other considerations to take into account that are not necessarily part of a model. Therefore, in many cases it is better to deploy a decision support system that will involve the people with industry expertise as part of the process.
Our experience shows that a successful advanced analytic price optimization project involves the following three steps:
Predict the price to volume relationship by leveraging both internal and external data, using a variety of machine learning techniques.
This requires understanding of internal customer demand and traffic, customer and product segmentation, lifecycle performance and other factors that influence the price. External factors can also be included such as competitor pricing, forecasts of events and weather etc. The actual data used depends on the industry. For instance, industries with limited capacity such as retail, car and equipment rentals, hotels, airlines have unique challenges as we describe in better forecasts start with understanding traffic.
The analytic methods most often used in this phase in modern systems is machine learning, where algorithms automatically do better in the future based on what was experienced in the past. As we noted above, this is not a “one size fit all” process. It requires intimate knowledge of the business drivers, data available and experimentation with various statistical methods.
Use the predicted price-volume curves as an input into a price optimization model to maximize profit or revenue while meeting volume and margin targets.
Depending on the type of business, constraints such as inventory, capacity and transportation can have a big impact. In addition there can be internal competition between products. In order to handle these you need to optimize based on what is driving the business, typically revenue, profit or market share, while maintaining the constraints mentioned above.
Another benefit of optimization is that it can provide prescriptive solutions – that is an answer to the question “what is the best way forward?” not just “what is a possible way forward?”. Including optimization as part of the process creates a dynamic pricing process that is in line with company goals and provides the best known way forward.
Companies need to facilitate effective change management, by leading with a detailed current state assessment and integrating the analytics decision support into their processes.
As we described above, there are many constraints that influence a company’s price strategy and detailed policies. This requires deep expertise in the specific market including knowledge of the customers, products and competition that often requires merchandiser or other sales involvement in the process.
The technology that can be developed around price optimization cannot typically replace this expertise and is often best deployed as a decision support system for these functions. Therefore, incorporating it into the current processes and allowing the experts to weigh in is an important part of the success of this type of effort.
[Name Redacted] is a half billion-dollar flash sales retailer primarily focused in the US. It covers a few different product categories, primarily women’s fashion, apparel, contemporary, traditional, accessories and luxury fashion. It also carries men’s fashion, home goods and kid’s products. It has a member base of about 9 Million.
Flash sales or Deal-of-the-day is an ecommerce business model in which a website offers a single product for sale for a period of 24 to 36 hours. Potential customers register as members of the deal-a-day websites and receive online offers and invitations by email or social networks. [Name Redacted] was challenged with this unique model in trying to figure out how to set the price of the first exposure of fashion products.
The analysis requires mining price data from competitive websites and sometimes, physical stores as well in order to figure out the price point of a similar style. In fashion, it is very hard to find the same product on any website because brands make the products differently for different retailers and it is very hard to find the exact same product somewhere else. The problem is not well studied and well understood and there are no good tools for it.
[Name Redacted] implemented a new analytic method for pricing that involved machine learning and optimization. This resulted in a 10% increase in revenue.
This what the three step process looked like:
The challenges faced were predicting the price for items that had not been sold before and estimating lost sales. Machine learning experimentation provided the ability to cluster similar products and use innovative regression to produce insights into new pricing opportunities.
This phase involved the issues of understanding the structure of the demand forecast and dealing with the demand of one style competing with others. This resulted in a novel formulation of the price model and creation of an efficient optimization algorithm that could be solved daily.
The result of steps one and two was the Price Optimizer software. However, it was important for [Name Redacted] to include the merchants in the pricing process. Therefore, every day the Price Optimizer suggests recommended prices for the first exposure style events that are starting the next day. It prices all styles for an event together for the next day in a single run. It takes about an hour and at the end of that run an email goes out to all of the merchants with recommendations for prices for the exposure styles for next day’s events.
We saw how the combination of data, prediction using machine learning and optimization enable an innovative approach to price optimization. Including the experts in the process by deploying a decision support system provdes the best of both worlds.
Accenture is a leading global professional services company, providing a broad range of services and solutions in strategy, consulting, digital, technology and operations. Combining unmatched experience and specialized skills across more than 40 industries and all business functions—underpinned by the world's largest delivery network—Accenture works at the intersection of business and technology to help clients improve their performance and create sustainable value for their stakeholders. With approximately 373,000 people serving clients in more than 120 countries, Accenture drives innovation to improve the way the world works and lives. Visit us at www.accenture.com.
Accenture Digital, comprised of Accenture Analytics, Accenture Interactive and Accenture Mobility, offers a comprehensive portfolio of business and technology services across digital marketing, mobility and analytics. From developing digital strategies to implementing digital technologies and running digital processes on their behalf, Accenture Digital helps clients leverage connected and mobile devices; extract insights from data using analytics; and enrich end-customer experiences and interactions, delivering tangible results from the virtual world and driving growth. Learn more about Accenture Digital at www.accenture.com/digital.
About Accenture Analytics
Accenture Analytics, part of Accenture Digital, delivers insight-driven outcomes at scale to help organizations improve their performance. With deep industry, functional, business process and technical experience, Accenture Analytics develops innovative consulting and outsourcing services for clients to help ensure they receive returns on their analytics investments. For more information follow us @ISpeakAnalytics and visit www.accenture.com/analytics.
This document makes descriptive reference to trademarks that may be owned by others. The use of such trademarks herein is not an assertion of ownership of such trademarks by Accenture and is not intended to represent or imply the existence of an association between Accenture and the lawful owners of such trademarks.
This blogpost is produced by consultants at Accenture as general guidance. It is not intended to provide specific advice on your circumstances. If you require advice or further details on any matters referred to, please contact your Accenture representative.