This document summarizes a presentation on using data for social good. It discusses several case studies where data and data science were used to help address social issues like homelessness, education access, and public health. Examples include using data to predict families at risk of eviction and homelessness in New York City, analyzing factors that contribute to successful online mentoring programs, and helping a land bank in Chicago prioritize properties for redevelopment. The presentation emphasizes bringing together different stakeholders like non-profits, technology companies, governments and community groups to tackle social problems through open data and collaboration.
The document summarizes Eddie Lin's work in data science for social good. It discusses his participation in the 2016 Data Science for Social Good Summer Fellowship at the University of Chicago, and his current work at DSaPP, which uses data and machine learning to help solve social problems. It outlines common machine learning tasks and how they are similar to concepts learned in kindergarten. It also describes typical social good project categories and emphasizes open source tools.
This document summarizes a presentation on using data for social good. It discusses several case studies where data and data science were used to help address social issues like homelessness, education access, and public health. Examples include using data to predict families at risk of eviction and homelessness in New York City, analyzing factors that contribute to successful online mentoring programs, and helping a land bank in Chicago prioritize properties for redevelopment. The presentation emphasizes bringing together different stakeholders like non-profits, technology companies, governments and community groups to tackle social problems through open data and collaboration.
The document summarizes Eddie Lin's work in data science for social good. It discusses his participation in the 2016 Data Science for Social Good Summer Fellowship at the University of Chicago, and his current work at DSaPP, which uses data and machine learning to help solve social problems. It outlines common machine learning tasks and how they are similar to concepts learned in kindergarten. It also describes typical social good project categories and emphasizes open source tools.
有人用勞力做公益,也有人用財力做公益,如果用資料力來做公益,不知道會擦出怎樣的火花?
2015年,我們打造一個「資料力,做公益」的交流與媒合平台,稱為「D4SG 計畫」 (Data for Social Good)。透過社群、黑客松、資料競賽、長期專案...等方式推動資料人與非營利組織的深度交流。這場演講將從資料人的角度分享如何與NPO/NGO合作,把冰冷的資料轉換化成有溫度的故事。
The document summarizes an emergency data analysis challenge presentation by Lee Shao-Fan and Yang Cheng-Han. It includes an outline, exploratory data analysis of emergency numbers over time by hospital level and individual hospitals, and a discussion of model building to predict total emergency numbers based on time, hospital, patient-doctor ratios and other factors for both hospital levels 1 and 2. Strange phenomena were noted in the emergency numbers for one hospital. Models were developed separately for hospital levels 1 and 2 to account for their differences.
The document discusses point clouds and how they are used. A point cloud is a large set of data points that represent a 3D object or environment. Point clouds can be created from laser scanners, cameras, sonar and other sensors. They provide a precise 3D representation of surfaces and are used in applications such as archaeology, mapping, self-driving cars, and more. The use of point clouds is growing across many industries as a way to efficiently capture 3D spatial data.
The document discusses spatial data and its applications. It describes how spatial data is produced through remote sensing from satellites and aerial photography. It then discusses various applications of spatial data in public sector planning, natural resource management, and enterprise spatial analysis. The document also introduces the concept of geo-internet of things (geo-IOT) and potential applications that combine spatial data and IOT.
Key Failure Factors of Building a Data Scientist TeamDSP智庫驅動
1. Building a successful data science team faces several key failure factors, including adding data scientists without a clear plan, prioritizing descriptive analysis reports over predictive models, and dealing with political conflicts between teams.
2. Other challenges include determining when a data management system is ready for data scientists to utilize, dealing with the lag time between data collection and seeing results, and navigating tensions between sales and data-driven decision making.
3. To avoid failures, companies need a planned approach with fast iteration, cross-functional collaboration in a dedicated data lab, secure funding, strong talent, and leadership to guide an experiment-focused culture.
Acer is introducing its BYOC (Build Your Own Cloud) platform to allow users to leverage their personal data and build applications. The presentation discusses how BYOC provides an open platform and global cloud infrastructure for collecting, storing, analyzing and generating insights from data. Examples are given of potential healthcare, home automation, insurance and education applications that could be developed using BYOC and its app development tools and analytics services. Q&A is held at the end to discuss opportunities to join Acer's IoT ecosystem.
有人用勞力做公益,也有人用財力做公益,如果用資料力來做公益,不知道會擦出怎樣的火花?
2015年,我們打造一個「資料力,做公益」的交流與媒合平台,稱為「D4SG 計畫」 (Data for Social Good)。透過社群、黑客松、資料競賽、長期專案...等方式推動資料人與非營利組織的深度交流。這場演講將從資料人的角度分享如何與NPO/NGO合作,把冰冷的資料轉換化成有溫度的故事。
The document summarizes an emergency data analysis challenge presentation by Lee Shao-Fan and Yang Cheng-Han. It includes an outline, exploratory data analysis of emergency numbers over time by hospital level and individual hospitals, and a discussion of model building to predict total emergency numbers based on time, hospital, patient-doctor ratios and other factors for both hospital levels 1 and 2. Strange phenomena were noted in the emergency numbers for one hospital. Models were developed separately for hospital levels 1 and 2 to account for their differences.
The document discusses point clouds and how they are used. A point cloud is a large set of data points that represent a 3D object or environment. Point clouds can be created from laser scanners, cameras, sonar and other sensors. They provide a precise 3D representation of surfaces and are used in applications such as archaeology, mapping, self-driving cars, and more. The use of point clouds is growing across many industries as a way to efficiently capture 3D spatial data.
The document discusses spatial data and its applications. It describes how spatial data is produced through remote sensing from satellites and aerial photography. It then discusses various applications of spatial data in public sector planning, natural resource management, and enterprise spatial analysis. The document also introduces the concept of geo-internet of things (geo-IOT) and potential applications that combine spatial data and IOT.
Key Failure Factors of Building a Data Scientist TeamDSP智庫驅動
1. Building a successful data science team faces several key failure factors, including adding data scientists without a clear plan, prioritizing descriptive analysis reports over predictive models, and dealing with political conflicts between teams.
2. Other challenges include determining when a data management system is ready for data scientists to utilize, dealing with the lag time between data collection and seeing results, and navigating tensions between sales and data-driven decision making.
3. To avoid failures, companies need a planned approach with fast iteration, cross-functional collaboration in a dedicated data lab, secure funding, strong talent, and leadership to guide an experiment-focused culture.
Acer is introducing its BYOC (Build Your Own Cloud) platform to allow users to leverage their personal data and build applications. The presentation discusses how BYOC provides an open platform and global cloud infrastructure for collecting, storing, analyzing and generating insights from data. Examples are given of potential healthcare, home automation, insurance and education applications that could be developed using BYOC and its app development tools and analytics services. Q&A is held at the end to discuss opportunities to join Acer's IoT ecosystem.