How Big Data will transform retail marketing
Marketers want to deliver to the right customer, at the right time, the most relevant communication, and digital technologies have greatly increased the number of 1-to-1 client communication channels in retail. Yet, the challenge of determining the ‘right’ communication for the individual client remains huge.
explores how Big Data technologies will transform retail marketing. Key aspects covered include:
- Targeting: How Big Data will replace customer segmentation with true 1-to-1 communication
- Measurement: How client history and basket analysis will decipher conversion, uplift and cannibalization
- Performance: How closed feedback loops create a learning system
- Innovation: How intelligent client applications will be powered by Big Data tech
- Cost: How full automation enables a massive scalability at low cost
Processing a large retail network on a smartphone
Long before ‘big data’ became a buzzword, retail networks have been among the pioneers in dealing with the large amounts of data that is produced by their supply chain and their point of sale systems. Yet, despite heavy IT investments, to date, the limitations and cost of the required infrastructure has left the reality far behind ambition and promise. This is particularly true for the richest retail data source: receipts generated by point of sale systems.
This technical whitepaper
explains how fundamental operations such as collecting and processing receipts for retail networks of up to 1000 stores can be done on a smartphone. The source code used by Lokad to produce the results exposed in this white paper has been made available as open source under a very liberal license (BSD) on GitHub.
Introduction to out-of-shelf monitoring technology
Few aspects of retailing are as fundamental as fully stacked shelves, and few concerns rank higher with an ever more demanding customer than product availability. On-shelf availability remains a huge challenge for the industry.
on out-of-shelf monitoring technology which gives an overview of
- Objectives of out-of-shelf monitoring systems
- Introduction to the technology
- Definition of performance characteristics
- Quantification of system capabilities and limitations
Testing and benchmarking out-of-shelf monitoring systems
Testing and benchmarking of competing out-of-shelf monitoring systems is an important step in quantifying the value of such systems for a retailer, and in identifying the most suitable vendor. After introducing the OOS domain in a first whitepaper, we take a closer look at how to best setup a trial and benchmark of competing OOS monitoring systems.
covers among other topics
- Benchmark criteria
- Methodologies for making OOS monitoring systems comparable
- Quantification of system profitability
- Project phases and execution
Spare parts inventory management with Quantile technology
The management of spare and service parts is as strategically important as it is difficult. In a world where most equipment manufacturers and retailers are operating in fiercely competitive markets, a high service level is often of high strategic importance.
However, managing a spare parts inventory efficiently still poses a huge challenge due to portfolio size, service level requirements and nature of demand. This whitepaper
discusses the challenges and current state of spare parts planning technology, and introduces quantile forecasting as a disruptive new approach to tackling the problem:
- Challenges in spare parts inventory management
- Why classic forecasting theory fails to address the problem
- Forecasting intermittend demand
- Introduciton to Quantile Technology for spare parts management
- Unlocking potential by optimizing service levels
Brochures and Presentations
Big Data Platform
Make the capturing, storing and exploiting of all of your company's transactional data in a fast, reliable and agile data platform simple, efficient and low cost. Combine this with smart applications that exploit this data in order to make smarter, faster operative decisions that address specific problems in the company. See also GitHub project
Lokad's forecasting engine
This video gives an overview of Lokad's core sales forecasting platform and explains how it works. Topics covered include
- Which models are used?
- How are the best models selected?
- How is seasonality and other patterns detected?
Quantile Forecasting TechnologyPart I
This video gives a first introduction to Quantile Technology and explains:
- What are quantiles?
- How do quantiles work?
- What are the advantages of quantiles?
This video explains why quantile forecasts outperforms classic forecasting methods particularly in three (common) situations:
- High service levels
- Intermittent demand
- Spiky demand
This video explains how forecast accuracy can be assessed, and how the accuracy of different forecasts should be compared (Runtime 7:30 min):
- Which assessment criteria should be used?
- How are the different assessment criteria calculated?
- How should the results be interpreted?
Help / Support
Send your questions at email@example.com
. In case of a technical issue, please give us a bit of context concerning your data and what you intend to do with this data.
Is your question of general interest? Do not hesitate to post on the Lokad Forums
. We monitor these forums closely, and do our best not to leave any questions unanswered.