Offer 1
Build our Pricing Engine
English summary
Students build an ML-based pricing engine for freight shipments, including a working pricing model and its data layer. They create connectors to live systems, develop central data models, work with real forwarder data, and test recommendations against real prices.
Overview
- Project details
- Build our Pricing Engine
Source excerpt · Page 1
- “# IDP @ nemox: Build our Pricing Engine” Page 1
- Organization
- nemox
Source excerpt · Page 1
- “# IDP @ nemox: Build our Pricing Engine” Page 1
- Project formats
- Degree levels
- Not stated on the project page
- Project goal
- Build a pricing engine that gives logistics operators reliable pricing recommendations.
Source excerpt · Page 1
- “build an ML model that gives logistics operators a price they can trust.” Page 1
Topics and work
- Subjects
- Application areas
- Methods and tools
- ML model
Source excerpt · Page 1
- “build an ML model that gives logistics operators a price they can trust.” Page 1
- abstracted connectors
Source excerpt · Page 1
- “build abstracted connectors that draw data from various live systems” Page 1
- real data from live systems
Source excerpt · Page 1
- “Clean data from live systems feeds the model.” Page 1
- ML model
- Activities
- Build an ML model for pricing recommendations
Source excerpt · Page 1
- “build an ML model that gives logistics operators reliable pricing recommendations” Page 1
- Build abstracted connectors for data from live systems
Source excerpt · Page 1
- “build abstracted connectors that draw data from various live systems” Page 1
- Build the data models used by the ML model
Source excerpt · Page 1
- “build the data models the ML model draws from, no matter where the data comes from” Page 1
- Work with real data from forwarders
Source excerpt · Page 1
- “work with real data from the forwarders that run on nemox” Page 1
- Test recommendations against real prices and assess their reliability and why
Source excerpt · Page 1
- “test the recommendations against real prices, and find out how reliable they are and why” Page 1
- Build an ML model for pricing recommendations
- Kinds of work
Requirements
- Required skills
- Hands-on experience with data science projects
Source excerpt · Page 1
- “Hands-on experience with data science projects (must)” Page 1
- Hands-on experience with data science projects
- Recommended skills
- Studies in statistics
Source excerpt · Page 1
- “Studies in statistics are a plus” Page 1
- Studies in statistics
- Eligible study fields
- Not stated on the project page
- Programming in the project
- Central
- Programming prerequisite
- Not stated on the project page
Practical details
- Team size
- 1–2
Source excerpt · Page 1
- “Number of students: 1–2” Page 1
- Duration
- 3 months full-time or 6 months part-time
Source excerpt · Page 1
- “Duration: 3 months full-time or 6 months part-time” Page 1
- Start
- ASAPNormalized date: asap
Source excerpt · Page 1
- “Begin: ASAP” Page 1
- Application deadline
- Not stated on the project page
- Work location
- nemox office in Munich, remote possible
Source excerpt · Page 1
- “Location: nemox office in Munich, remote possible” Page 1
- Location mode
- Hybrid
Source excerpt · Page 1
- “Location: nemox office in Munich, remote possible” Page 1
- Working language
- Not stated on the project page
Learning and support
- Learning opportunities
- Not stated on the project page
- Support offered
- Not stated on the project page
Application and contacts
- Contacts
- isabel@nemox.ai
Source excerpt · Page 1
- “Contact: isabel@nemox.ai” Page 1
- Alexandra Garatzotianni, MBA, M.Sc., M.A.
Source excerpt · Page 1
- “ERI Supervisor: Alexandra Garatzogianni, MBA, M.Sc., M.A.” Page 1
- isabel@nemox.ai
- How to apply
- CV and transcript of records, plus a short note on why you are a great fit. Optional: a past ML project or GitHub repo.
- Further information
- Not stated on the project page