Skip to main content Skip to Footer


August 04, 2015
The art of packing your analytics tool-bag
By: Sumeet Mahajan & Desmond Torkornoo

As consultants, we travel frequently and widely for various projects and to meet clients. Because we are on the road so often, we always have a half-packed suitcase ready to go. These trips vary in length and location, so as the exemplars of efficiency that we are, we are always trying to minimize, quite literally, the unnecessary baggage. Similarly, the organizations we work with, on many different kinds of advanced analytics initiatives, also seek to minimize their unnecessary baggage. One such baggage we see quite often is the choice of analytics itself, where the types of tools and techniques used should be as simple as possible, but not too simple.

As simple as possible

The decision to use, or to not use, sophisticated analytics depends largely on the objective of your initiative and the kind of models you are building. These models could range from simple center-of-gravity models to advanced inventory, pricing, network or transportation optimization models.

Based on our company’s collective experience of over 350 analytics studies, we recommend that this decision should be made from the viewpoint of each input parameter and the model’s expected sensitivity to it. For instance, if we are running a center-of-gravity analysis (or even a 10-year distribution footprint analysis), one of our primary input parameters will be the forecasted demand for coming years. Because of the strategic nature of our analysis, and hence of the input parameters, our estimates don’t need to be overly accurate and we should not spend excessive time and effort to get to a higher level of accuracy by using advanced mathematical techniques. In short, one should not reach for a baseball bat when a rolled-up newspaper will do the job of swatting a pesky little fly.

However, the same input parameter (forecasted demand) needs to have a very high accuracy level when we are running a tactical weekly freight optimization model. So while in the first case a simple top-line forecast would suffice, in the latter case a bottom-line forecast enhanced by predictive analytics and machine learning techniques would provide the required level of quality and accuracy. Almost all inputs, to any type of analysis, can be viewed as a tradeoff between accuracy and level of difficulty.

Not too simple

While we need to keep things as simple as possible, we should leverage advanced mathematics and analytics when the benefit far outweighs the difficulty. In one of our end-to-end optimization studies, we were dealing with complex bills of materials (BOMs) that were 20 tiers deep, with hundreds of raw materials and many components going into a single finished product. And almost every finished product was unique. By using advanced computation techniques we were able to flatten the bills of materials from 20 to 3 tiers while using a mix of machine learning techniques to aggregate similar products at the sourced component level. This approach reduced the complexity of the analysis, and brought the run time down from hours to minutes while maintaining the required accuracy of the model.

In another example, demand forecast happened to be an operational input and required a high level of accuracy. So instead of using forecasts simply based on trends and seasonality, we were able to further enhance the forecasts based on factors such as internal and external events and competitor prices using regression analysis. There are many other instances where we have had to estimate labor and freight costs, transit times between zones, product weights, and other missing or incomplete data sets using simple to advanced estimation techniques.

As shown in the illustration below, the spectrum of sophistication for data cleansing and enriching is wide as is the range of analytical applications. As the saying (which we’ve just made up) goes, “a useful bag is rarely light but a heavy bag is not always useful.” So, pack lightly but don’t forget your toothbrush.

About Accenture

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

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


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

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.

Popular Tags

    More blogs on this topic