Customer
LunarLight is a smart AI platform that centralizes transportation data for efficient decision-making when it comes to rail freight from A to B. It’s all about speed, maximizing wagon turnover, loading efficiency, and saving transport market operators both time and money.
LunarLight empowers wagon forwarders and cargo owners to track their cargo and timing seamlessly. It constructs personalized customer dashboards based on the structured data they upload to the platform. By analyzing this data, the platform provides valuable insights for well-informed decision-making. For instance, LunarLight sends notifications when any traffic anomalies arise.
Background
LunarLight started with implementation for a group of 6 national state-owned railway companies. Overall, the idea was to show how the cargo is transported from the factories through the country, reaching out to port terminals.
LunarLight was one of the first available tools for operators in the transport market to obtain a comprehensive view of their cargo and wagon’s current location, routes, and potential changes in an estimated time of arrival (ETA).
Challenge
In order to deliver precise analytics and provide an outstanding customer experience, LunarLight needed to tackle the challenge of onboarding customer data, which often arrives in varying structures. Transportation data can differ not only between customers but also within a single customer’s historical data due to changing time periods. Each logistics company has its unique datasets with varying columns and column names. Additionally, the values within these columns can evolve over time. For instance, consider a railway station code in Eastern Europe, which expanded its network and introduced new stations, leading to changes from 4-digit to 5-digit and eventually to 6-digit codes.
Further complexities arose when carriers had to transport cargo across different countries and utilize various railway companies while ensuring the tracking of wagons and freight throughout the process. The primary hurdle they faced was dealing with inconsistent data from European railways. Each railway used different data formats, systems, and sometimes even non-Latin alphabets. Additionally, variations in track width in some railways required changes to wagon wheel pairs or cargo reloading onto different wagons. This often led to alterations in wagon numbers that were not accurately reflected in the records. All of these issues made tracking wagons from one country to another extremely difficult.
Discovery of Solution
LunarLight was at a crossroads: they had to decide whether to invest time in developing their own data onboarding feature, potentially delaying the main product release, or to opt for an existing tool, saving resources for the core functionality development.
After careful consideration, they opted for Datuum as their data onboarding partner due to specific key criteria:
- Automated data mapping
- AI-powered engine recognizing data meaning and proposing the best mapping
- Visual data mapping for collaborative data onboarding and accuracy checks
- Compatibility with legacy data
- User-friendly no-code interface that allows hiring only one data analyst to handle data from several customers
- Capability to handle various data types from different sources
- Simple process for cleaning data and removing anomalies
- Adherence to security and compliance policies
“We were looking for an onboarding partner. Since Datuum implementation on the customer cloud was very easy, we are excited to go forward and see what benefit of using a ready tool we can get and how more efficient data preparation will become,” – Mariia Solianik, CEO at LunarLight.
Implementation
While LunarLigh was focused on solving all the logistics and visualization challenges, Datuum played a crucial role in setting up a data consolidation process for railway companies. It involved transferring the source data sent in different .CSV and .XLS files to target storage in MongoDB, enabling further analysis and visualization. Moreover, it unlocked the potential to incorporate data from other railways, even with variations in data schemes.
Implementing Datuum was a breeze, taking only a few days. Most of the work involved configuring the Amazon server as the destination for LunarLight’s onboarded data.
Results and Impact
LunarLight is highly satisfied with Datuum’s data onboarding tool. With minimal effort, its CSMs can seamlessly onboard customer data onto the platform and swiftly generate insightful dashboards. Additionally, thanks to Datuum, LunarLight can scale gathering data from diverse railways across Europe despite variations in structure, format, and standards. This enables them to offer customers a comprehensive view of routes, cargo, and wagons throughout Europe.
