microbase pitch on SCEWC 2024

We are exhibiting at S23, HAII3 Innovation Playground.
Feel free to come and visit us!

#smartcity #SCEWC #Barcelona

Transcript

1. Confidential 1 Micro Urban Planning AI Dashboard
2. Confidential The Common Global Challenges We Solve Mismatch between supply and demand for housing and public services Urban area Suburban area • housing shortage • Rising rents and homelessness • Increase in vacant houses • Huge costs for maintaining aging infrastructure
3. Confidential Possibility of Urban Redesign through Utilization of Vacant Houses Residential needs Large Small Barcelona: 200,000 empty homes Madrid: almost 188,000 empty homes Barcelona: 172,575 empty homes Data source: census (2021) Potential supply of housing If house is cheap, it sells. 90% house have been sold!!
4. Confidential Out solution and core technology 4 Not properly priced or sold. Price gap between the final contract price and the initial sales price affects distribution. Vacant houses not all coming to market depending on owners. Vacant house is not same as Normal real estate. Because the owner doesn’t consider selling their own houses. Get and access to the owners before the house become empty by future prediction of Vacancy and Move-in Help the owners to accelerate selling their houses by AI recommendation on how to sell, from the contracted price. Expansion in 8 municipalities in cooperation with a major bank Use case of Japan future prediction AI dashboard
5. Confidential Get and access to the owners before vacant house by MiraiE.ai 5
6. Confidential Get and access to the owners before vacant house by MiraiE.ai 6 NPWJF
7. Confidential ** Patent obtained 7 ⽉次使⽤量データの例（ Aさん宅） 実際に閉栓 M ira iEによって空 き家になると予測 過去から現在 将来 使⽤量 (㎥) （ 現在） Resident-data Subscriber-data etc. Open-data Third-part- data Latitude & longitude data(Assigned to the residential unit) ①Combining data ③Forecast ②Model learning GIS Combine data with overlapping positions on the map Basic Resident Register(Subscriber information) Water/gas/electricit y consumption Registry registers Training data of vacant houses Building data Output Input Data * AI forecast ** 5-year prediction accuracy 92% Conducted demonstration tests in 4 cities, Toyota city and a major gas provider Data on future vacancy projections (probability). *The above data is just an example. It is not necessary to provide all of them. How does MiraiE.ai work? 4 million dwellings data trained NPWJF
8. Confidential 8 Future Forecast As Urban OS Data for Urban Redesign Optimizing urban infrastructure renewal Support for efficient second -hand housing distribution STEP１ Assess the actual situation and predict the future Preparation STEP２ Provide solutions for regional redesign Matching of vacancies with prospective residents Forecast next vacancy and occupancy of houses as Build basic data set By providing owners of vacant reserve homes with a simulation of the sale price. By optimizing the number of applications by using future vacancy forecasts By identifying future vacancies area and prioritizing infrastructure renewal and downsizing Use case of Japan
9. Confidential We are looking for Municipalities and data partners. We look forward to seeing you at our booth “S23”! 9 HIROAKI SENGOKU CEO , Ph.D Date Scientist NORIKO OKUMA Business Planning Manager From Tokyo, Japan “S23”