Transmetrics, a logistics startup, is helping freight transport companies and logistics service providers optimise operations via technologies such as artificial intelligence, data mining and predictive analytics.
“We help our customers save a significant portion of their operational costs, in particular, transportation costs. We do this by helping them plan for optimal transportation capacity,” says Asparuh Koev, CEO and co-founder of Transmetrics.
Prior to Transmetrics, Koev and his co-founder, ran a consulting firm for IT projects within the freight transport sphere where they noticed numerous problems facing the sector when it came to capacity optimisation.
As consultants, their hands were tied as what was required was a systematic software-based approach. Hence the decision in 2013 to step out of the consulting arena and build a software product.
According to Koev, Transmetrics helps customers plan for optimal transportation capacity by data cleansing and enrichment via artificial intelligence and advanced statistical methods as well as improving forecasting and optimization.
In Koev’s opinion, the logistics industry has to look at new methods in order to become more efficient amid challenging market conditions and low capacity utilisation issues. AI, big data, and predictive analytics are the right toolboxes to fix current problems, he believes. However, Koev warns the drawbacks of utilising such technologies are that the more you optimise the system the less resistant it becomes to unforeseen events.
According to Koev, one of the company’s largest customers is using Transmetrics’ predictive analytics software to forecast expected shipping volumes one week in advance and to optimise the amount of trucks needed to deliver all its shipments. By adopting the technology, the company has been able to reduce truck departures by 25% and save total costs by 8% to 9%.
Koev tries to pour cold water on a common perception that AI will inevitably lead to job losses in the logistics field.
“In reality,” he says, “computers cannot be people because they lack creativity, imagination, and they cannot think abstractly. Artificial intelligence is a set of algorithms which can provide very complicated outputs and decisions based on incoming data.”
For companies who want to venture into implementing AI and predictive analytics, Koev’s advice is to start with improving data quality.
“The biggest mistake is starting from the end – optimisation – rather than from the start. If you start from the end, you are going to have very disappointing results because of the initial poor data quality,” Koev warns.