Health prediction model building machine | Information dissemination media for research and development TEGAKARI

Case No.PC-10619A customer who saw this asked us about a machine for building a health prediction model.
Using epidemiological data, the purpose is to construct a predictive model for future health and conduct causal search between measurement items, and we would like a PC with the fastest possible processing speed within a budget of 280 million yen.

Currently, the analysis is performed in Python, and the packages RandomForest, LightGBM, LiNGAM, and pgmpy are used.In addition, the maximum amount of data that can be handled is 1 rows x 1 columns, and the current problem is that the calculation time is extremely long.
The package used does not require GPU performance, so GPU performance is currently not emphasized, but we hear that there are plans to implement deep learning and handle larger-scale data in the future.Based on that point, I would like a motherboard that can add a video card.

Specifically, we are contacting you regarding the following conditions:

・CPU: AMD Ryzen ThreadripperPRO 5975WX or 5995WX
・Memory: 256GB or more
・Storage: 4TB SSD or more
・OS: Windows 11 Professional 64bit
・Software used: python (RandomForest, LightGBM, LiNGAM, pgmpy, etc.)
・Budget: Within 280 million yen

Based on the above information, we proposed the following configuration.

CPU	AMD Ryzen ThreadripperPRO 5995WX (2.70GHz 64 cores)
memory	512GB REG ECC
Storage 1	4TB SSD S-ATA
Storage 2	16TB HDD S-ATA
video	NVIDIA Geforce RTX4090 24GB
network	on board (1GbE x1, 10GbE x1)
Housing + power supply	Tower type housing + 1600W
OS	Microsoft Windows 11 Professional 64bit

This is a scaled-up configuration based on the configuration of inquiry case PC-10619.
Specifically, in order to improve parallel processing performance, we changed the CPU to a higher model and doubled the amount of memory installed.

You said that the priority of the video card is low, but even if the CPU is a top-end product, in addition to being able to afford the budget, I heard that there are plans to implement Deep Learning in the future, so I decided to use the high-end model I chose the NVIDIA Geforce RTX4090 24GB which is .

The Geforce RTX4090 24GB is equipped with 16,384 CUDA cores, 512 4th generation Tensor cores, and 24GB of GDDR6X VRAM, so it can be expected to be used for Deep Learning. If you don't need to support DeepLearning, you can change it.

Motherboards are selected to ensure expandability.
If you have a specific request for expansion, we can adjust the configuration accordingly, so please let us know.

The configuration of this case study is based on the conditions given by the customer.
We will flexibly propose machines according to your conditions, so please feel free to contact us even if you are considering different conditions than what is listed.

■ Keywords

・What is Python?
Python is an object-oriented programming language copyrighted by the Python Software Foundation (PSF).Its programming syntax is simple, making it highly readable, and it also features a wide variety of components, such as libraries and frameworks, that are suitable for different purposes.A popular language for programming beginners to advanced users.

reference:Python *Jumps to an external site

reference:[Feature Article] Programming language Python Why is it so popular? --Tools to accelerate Python programming * Jump to our owned media "TEGAKARI"

・What is Deep Learning?
DeepLearning is a type of machine learning that uses multilayer neural networks to perform advanced pattern recognition and prediction.Since it generally requires a large amount of data, it is considered to be an effective method when data are abundant.
DeepLearning is also widely used in fields such as image recognition, speech recognition, and natural language processing.Because it can learn complex features and relationships, it can achieve higher accuracy than traditional machine learning methods.