Service providers ranking among the top 20 in our directories are awarded our Top Vendor recognition for the respective directory.
codecentric is an IT consulting firm for agile software development with 16 locations. At our company, top talents meet innovative technologies & modern methods.
Contact the vendor and get feedback on your queries in a timely manner.
Contact the service provider and receive an appropriate offer in a timely manner.
// Partnership and passion for sustainable solutions
We accompany you as a partner. That is our commitment and aspiration. Because technology is not everything. It depends on the right way to develop solutions and implement them in the company.
// Questioning each other critically
We focus on communication between people. This is the only way we can achieve good results for and with you. This determines our work in the project. We benefit from our codecentric culture: we are passionate and goal-oriented in finding solutions and are also direct, honest and not afraid to ask critical questions. For us, this also includes openly addressing unpleasant topics in order to achieve the best possible result together with our customers.
You can find more information about us and how we work here:
https://www.codecentric.de/arbeitsweise
Contact the vendor and get feedback on your queries in a timely manner.
Fast order processing is a decisive competitive advantage when it comes to the door-to-door delivery of beverages and other foodstuffs. A maximum of 120 minutes should therefore pass from ordering in the online store to delivery to the doorstep.
To orchestrate driver logistics, flaschenpost relies on machine learning to create forecasts for logistics processes and supply chains. Large amounts of data are processed and analyzed to identify patterns and trends that are helpful in predicting the availability of drivers and estimating the duration of work steps. The more precise the estimates are, the more accurate the route planning results for the drivers will be.
// Team structure
A joint team consisting of developers from flaschenpost and codecentric was formed for the duration of the project. The team consisted of a mix of experienced and young data scientists and data engineers who used agile methods such as Scrum to continuously improve and operationalize the algorithms.
// Milestones of the project
An important milestone was to expand the forecasting portfolio so that further steps in the machine learning supply chain could be optimized. In addition, various solutions for the automation of complex data and machine learning pipelines were investigated and implemented. These were intended to reduce the effort required for administrative and operational tasks. It was also important to be able to clearly display and compare the metrics of different algorithms. This allows the best model to be identified quickly and a systematic investigation to be carried out into which data leads to an improvement in an AI model.
// Technical design
The settings that need to be defined before training a model and that influence its performance were automated. Monitoring and reporting was expanded in a meaningful way so that the team has an even better overview of the performance of the forecasting portfolio. The main programming language was Python, which supports all relevant machine learning and data engineering frameworks in addition to excellent integration with Kubernetes and Azure. The technology stack also included Kubernetes, MLFlow, HyperOpt, FastAPI and streamlit, among others.
The optimized and expanded logistics forecasting portfolio of flaschenpost SE now runs robustly and is easy to expand. The solution enables a systematic analysis of the data and thus contributes to an improvement of the AI model. Through automation, tracking with MLFlow and a dashboard that displays the metrics of the individual algorithms, the cycle time from model development to evaluation in live operation has been significantly reduced.
The developers at flaschenpost are now able to transparently view the data involved, training parameters and the utilization of the models; the data can also be easily adjusted. The models developed in this way enable flaschenpost to predict and plan driver logistics even better before, during and after a delivery tour. Automation has led to a reduction in IT infrastructure costs as well as an increase in data analysis speed.
Contact the service provider and receive an appropriate offer in a timely manner.
Contact the service provider and receive an appropriate offer in a timely manner.
| RATING | PERCENTAGE | DISTRIBUTION |
|---|---|---|
| 5 stars | 96.2% |
|
| 4 stars | 3.8% |
|
| 3 stars | 0% |
|
| 2 stars | 0% |
|
| 1 star | 0% |
|
Place to be in Solingen for a first snog...😉
Really chic for a workplace......
