Next-Generation Logistics Simulation via Logistics AI "EIQ_AI"

Building data models that train on shipping data to predict center capacity with high precision

Language Switcher in AI Portal

Logistics AI "EIQ_AI" is a groundbreaking logistics simulation system combining EIQ analysis and machine learning based on historical shipping data. By creating a baseline data model from a single set of shipping data and using the number of destinations (E) and number of items (I) as keys to train the AI on 100–200 sample model data points through machine learning, it delivers high-precision AI predictions for 164 rank-based variables (number of lines, loose items, cases, pallets, volume, weight, etc.) and automatically generates EIQ matrix tables.
We explain this revolutionary data model construction method and the distribution center logistics simulation procedures through the interface of our free software (TCalc EIQ_AI).

đź”° For First-Time Visitors: Recommended Steps

If you are new to this system, reviewing the pages in the following sequence will help you smoothly understand the mechanics of our logistics simulation.

  1. First, understand the overall concept at Explanation of TCalc EIQ_AI
  2. Check the actual operational feel at TCalc EIQ_AI Software (Prototype) Screen Image
  3. For a deeper dive, read the Data Model Explanation or see the "Data Model Generation Steps" below

* If you have downloaded the freeware, please also check the Folder Usage Guide.

Development Purpose of Logistics AI "EIQ_AI" Freeware

The EIQ_AI software is an educational and learning support tool designed for logistics practitioners and students to gain hands-on experience with "building data models using logistics AI" and conducting "distribution center logistics simulations." Prototype versions have already been introduced in lectures and research at two universities, with plans for a full freeware public release in the future.
This system is an AI-extended version of the "TCalc" series—a logistics analysis tool advocated by our institute—designed to visualize and automate the specific calculation process of EIQ analysis and the estimation of required area and personnel.

🎯 Recommended Logistics Simulation Software for These Needs & Challenges

EIQ Analysis and Logistics Simulation Based on Fractal Theory

The late Dr. Shin Suzuki proposed that "distribution centers are fractals." This implies that shipping data is also fractal in nature.
Just as a mulberry leaf maintains the same shape (self-similarity) regardless of whether it is small or large, shipping data maintains the composition ratios among its components even as physical volumes fluctuate.
In summary, even when shipment volumes fluctuate depending on the E count and I count, shipping data maintains the composition ratios of the EIQ matrix table derived from EIQ analysis.
By leveraging this characteristic, our system performs actual calculations by varying the E and I counts of the data model, then trains the logistics AI on these aggregated results using machine learning, enabling extremely accurate predictions.

High-Precision Data Model Design via Logistics AI Ă— Machine Learning

Fusing 30 years of logistics consulting expertise with state-of-the-art machine learning algorithms (Microsoft.ML), our system instantly derives optimal logistics design data models. From minimal key inputs—the number of delivery destinations (E) and item counts (I)—it automatically generates capacity forecast models for logistics simulation covering detailed rank-based variables such as line counts, loose item quantities, case counts, pallet counts, volume, and weight.

✨ 3 Key Values Delivered by Logistics AI "TCalc EIQ_AI"
  1. Dramatic Time Savings: Instantly outputs EIQ analysis and complex logistics simulations that previously required extensive manual effort by creating data models through machine learning.
  2. Resilience to Fluctuations: Even during extreme spikes or drops in shipping data between peak and off-peak seasons, it delivers realistic predicted values (164 variable items) while preserving ratio proportions.
  3. Eliminating the Black Box: By visualizing how the logistics AI trained and made predictions through machine learning, it provides clear, convincing rationale for both learners and practitioners.
1. Training and Building Data Models with Logistics AI

Load arbitrary shipping data and execute machine learning using the SDCA regression model. Generates a data model functioning as the "Logistics AI brain" capable of forecasting capacity across 164 rank-based variable items.

Details: View steps for data model generation using EIQ_AI
2. EIQ Analysis Forecasting and Logistics Simulation

Using the generated data model, instantly output six prediction matrices with distinct characteristics (shipping frequency, weight, volume, etc.) to visually evaluate and perform a logistics simulation of distribution center capability.

Logistics DX: View capacity forecasting & matrix visualization features of TCalc EIQ_AI

From Theory to Practice: Download Logistics Simulation Freeware

For practitioners working on field improvements and distribution center design, as well as students researching data models for logistics AI and machine learning,
we offer a free release of our logistics simulation freeware (TCalc EIQ_AI) capable of practical capacity forecasting from your shipping data.

📥 Download Freeware (Prototype Version) Free 🏢 Logistics Technology Research Institute Top

Future Roadmap (Expansion Plans)

đź“Ś Update Notice Ahead of Official Release:
Future official releases will introduce features to separate predictions for "loose shipments" and "case shipments" in logistics simulations. Furthermore, by incorporating total order volume (Q) and total line counts (R) into the parameters, it will evolve into a universal "fractal logistics AI data model" capable of handling logistics site fluctuations across all industries and scales.

Technology Stack Explanation: Machine Learning with Microsoft.ML (ML.NET)

This portal utilizes "ML.NET," allowing custom machine learning data models to be built and integrated natively within a .NET environment. It achieves advanced logistics AI capacity forecasting entirely in C# without relying on external languages like Python.

1. Core of ML.NET
  • Cross-Platform: Runs on Windows, Linux, and macOS.
  • High Performance: Optimized since .NET 6.0 for high-speed calculation processing.
2. SDCA Regression Model
  • Efficient Algorithm: Enables fast machine learning while keeping memory consumption low.
  • Optimal for Logistics Simulation: Constructs data models that accurately forecast weight, volume, and required space from factors such as E and I.
Submit Inquiries / Feedback via Dedicated Form