Blog /

AI Forecast demand


minutes reading

Leer versión en españolLire la version française

How AI-Powered Forecasting Can Unlock the Optimal Fleet Strategy

The logistics industry is facing unprecedented challenges with fluctuating customer demands, volatile market conditions, and constant pressure to reduce costs. For operations managers, finding the optimal fleet configuration can seem like an insurmountable hurdle. This involves determining the ideal number of vehicles of the right types available at the right times to meet customer demand without excess or shortage.

Achieving this optimal balance is crucial for logistics service providers' (LSP) operational excellence. It not only minimises costs associated with surplus vehicles but also ensures the ability to scale operations rapidly when demand surges, enabling LSPs to maintain their competitive edge. However, traditional forecasting methods often fall short in the face of today's dynamic market conditions.

Artificial intelligence (AI) and machine learning (ML) have emerged as game-changing technologies in this regard. They enable LSPs to revolutionise their medium-to-long-term capacity planning with sophisticated predictive analytics, enabling a more proactive and precise approach to fleet management.

In this article, we discuss the transformative applications of AI and ML for operations departments, focusing on their impact on fleet and team productivity. We will also examine how accurate medium-to-long-term forecasting can be pivotal in devising and implementing the optimal fleet strategy for any given scenario, ultimately enhancing the LSP's ability to meet customer needs and thrive in a competitive market.

Why AI forecasting is a game-changer for ops departments

The traditional approach to fleet management, which relies on historical data and intuition, often falls short in today's volatile market. This is where AI-powered forecasting comes in, transforming how LSPs approach capacity planning and fleet optimisation. By harnessing the power of machine learning, LSPs can gain unprecedented insights into future demand, enabling proactive decision-making and a more agile response to market fluctuations.

1. Predictive Capacity Preparation

AI and ML forecasting models provide precise predictions about the expected number of orders or shipments across different areas or routes. This predictive insight enables companies to determine the type and number of vehicles required to fulfill these orders efficiently. By anticipating demand, ops managers can proactively plan the optimal fleet capacity for each area or route with weeks of anticipation. 


All of this is made possible, not only with the inclusion of advance data analysis and machine learning capabilities that provide greater accuracy, but also by using dashboards and reports that can provide insights about the future, with monthly and weekly data facilitating the strategic planning of the capacity needed in the medium-to-long term. Take, for example, the following visualisation:

From here, operations managers and agents can:

  • Monitor and evaluate forecasted demand against capacity and business plans. By comparing predictions with actual performance to assess past strategies' effectiveness, ops managers can identify improvement areas and make data-driven adjustments to optimise future plans.
  • Analyse weekly demand trends across multiple scenarios. Through examining completed orders, forecasted demand, and optimistic projections, it is possible to gain insights into patterns, seasonality, and potential fluctuations.
  • Evaluate vehicle capacity demand to anticipate future needs. The assessment of vehicle use over time enables the identification of usage trends and helps to anticipate future vehicle requirements to ensure optimal fleet composition and availability.

Advanced forecast calculations uncover demand trends and pinpoint the specific vehicle requirements for each region and route. Armed with this granular insight, operations managers can proactively calculate optimal fleet capacity weeks in advance, ensuring optimal resource allocation. This can be achieved through strategic pre-bookings or by maintaining a dynamic pool of vehicles primed for deployment. Such foresight minimises the risk of unexpected capacity shortages or costly surpluses, ultimately optimising resource utilisation and driving down operational costs.

2. Trend and seasonality assessment

Leveraging advanced forecasting capabilities empowers LSPs to proactively anticipate seasonal fluctuations and other temporal variations that impact demand and supply. This foresight enables the integration of flexibility into capacity planning, ensuring smooth operations during peak seasons and efficient resource allocation during slower periods. By continuously monitoring evolving trends, LSPs can stay ahead of the curve, adapting swiftly to any shifts that may influence their operations.


Consider the heightened demands of peak seasons like Black Friday and Christmas, known for dramatic surges in consumer purchases. By harnessing AI and ML forecasting models, LSPs can accurately predict demand fluctuations for specific sectors within a given region, as illustrated in the plot below.

These forecasts might indicate a significant increase in shipments during these periods compared to regular weeks –  even as much as 20%.

Armed with this advanced notice, operations managers can proactively arrange for additional trucks and drivers to be available during these peak periods, ensuring timely deliveries and optimal fleet utilisation. This proactive approach, leveraging trend monitoring and peak detection capabilities, means that LSPs can effectively manage seasonal fluctuations, ensuring they have the right capacity to meet demand without overextending resources or sacrificing service quality.

3. Data-based decision-making with accurate scenario simulation

Advanced forecasting tools enable LSPs to simulate a wide range of potential future scenarios that could impact operations. These scenarios encompass external factors like holidays, strikes, or weather events, as well as internal business developments like onboarding new clients, expanding into new areas, or introducing new routes. 

By simulating these scenarios, LSPs can proactively develop and refine contingency plans, ensuring they are well-prepared to navigate both expected and unexpected situations. This ability to anticipate and adapt is crucial for maintaining operational resilience and delivering consistent service in the face of uncertainty.


Tools like the Forecast Scenario Simulation, a key feature of Ontruck's AI Tech Forecast & Capacity Planning module, enable LSPs to model the potential impact of major disruptions or transformative business changes, such as expanding into new service areas or onboarding significant new clients. By simulating these scenarios, LSPs can make informed decisions about resource allocation, optimal fleet capacity, and operational strategies, ensuring they are well-prepared for both challenges and opportunities in the ever-evolving logistics landscape.

Take the graph above, where the light red line illustrates the forecasted impact of a new tender on expected volumes a logistics company will confront over the next few months. This allows the operations manager to adjust fleet capacity proactively to meet the anticipated demand, ensuring optimal fleet utilisation and cost efficiency.

Final thoughts

The practical and effective use of accurate forecasts enables LSPs to achieve optimal fleet capacity, ensuring resources are efficiently scaled and dynamically adjusted to meet both day-to-day operational needs and future demand trends. This streamlined approach not only reduces costs but also significantly enhances service quality across the board.

From our experience, understanding and adopting these technologies is no longer a luxury for LSP operations managers but a necessity. Implementing AI and ML fosters a proactive approach to logistics management, supporting LSPs in anticipating challenges and opportunities and responding confidently. By embracing these innovations, LSP leaders can not only prepare for the future but also shape it, ensuring their organisations remain competitive and resilient in an ever-changing market.


Kuczyńska-Chałada, M., Furman, J., & Poloczek, R. (2018). The challenges for logistics in the aspect of industry 4.0. Multidisciplinary Aspects of Production Engineering, 1(1), 553-559.

Articles that may interest you

Innovative strategies for digital freight matching: how to find the perfect fit with automation

Discover how AI and automation can transform freight matching, surpassing load boards to boost efficiency for shippers and carriers.

Read more

Fine-Tuning Dynamic Route Optimisation to Redefine Efficiency in Logistics

Rising costs are squeezing LSPs, but dynamic route optimisation offers a solution. Learn how it works, the different tools and their unique capabilities.

Read more

KPIs for Transport and Logistics: Types, Examples and How to Use Them

Transportation KPIs measure performance at each phase of the supply chain. Find out how to implement them in your business.

Read more

How AI-Powered Forecasting Can Unlock the Optimal Fleet Strategy

AI enables LSPs to calculate optimal fleet capacity, proactively address demand fluctuations and simulate future scenarios for informed decision-making.

Read more

En OnTruck os damos las gracias por este 2016

Despedimos el 2016 muy contentos con los objetivos alcanzados y muy agradecidos por las relaciones comerciales y profesionales que hemos desarrollado

Leer más

¿Qué peso tiene el transporte de mercancías en Cataluña?

Cataluña al frente de la logística en España. Es el gran referente nacional en el transporte de mercancía y de los más importantes en la Unión Europea.

Leer más

Los desafíos de la UE para el sector del transporte de mercancías

El año 2017 se presenta repleto de desafíos para Bruselas en el sector del transporte de mercancías jugando además un papel muy importante que afecta a todos.

Leer más

Los plazos de pago en el transporte se situaron en los 85 días de media durante 2016

El sector del transporte por carretera asume un repetido incumplimiento de la Ley de Morosidad aprobada en 2010 con una media de periodo de pago de 85 días

Leer más