1. The document discusses various social media and video sharing platforms and tools for integrating them, including YouTube, Twitter, Flickr, iTunes, and Facebook.
2. It mentions several services that allow embedding or sharing content between platforms, such as CDTube for YouTube, ZonTube for Amazon, and amz.ly for shortening Amazon URLs for Twitter.
3. Programming languages and APIs mentioned include JavaScript, jQuery, Twitter API, and YouTube APIs for building integrations and plugins.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
The document provides an introduction and background about the speaker, Kenichi Matsui. It discusses his career experience working for several large companies in software development, communications, and consulting. It then covers some of his current responsibilities related to data analysis and machine learning as a data scientist and group manager. Specific topics covered include an overview of data science skills and roles, machine learning techniques like classification and regression, and data analysis competitions.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
The document provides an introduction and background about the speaker, Kenichi Matsui. It discusses his career experience working for several large companies in software development, communications, and consulting. It then covers some of his current responsibilities related to data analysis and machine learning as a data scientist and group manager. Specific topics covered include an overview of data science skills and roles, machine learning techniques like classification and regression, and data analysis competitions.
DB TechShowcase Tokyo - Intelligent Data PlatformDaiyu Hatakeyama
?
AI (Artificial Intelligence) が様々なアプリケーション/サービスに組み込まれ始めて、それをうみだす原動力ともいえるデータプラットフォームもその立ち位置を変えてきています。次期SQL Server 2017には、Machine Learning Servicesが同梱され、まさに次世代のデータプラットフォームの一つの形といえるでしょう。このセッションでは、System of Record から、System of Insight へとその価値を変えていく最新のData Platformの世界をご紹介します。
27. KGI: 日次の売上
tbl_receipt
カラム名 データ型
user_id INT ユーザーID
purchase_dt DATETIME 購入日時
unit_price INT 課金額
SELECT
SUM(unit_price),
DATE(purchase_dt) AS Dt,
FROM tbl_receipt
GROUP BY Dt
ORDER BY Dt
27
31. 売上と DAU の相関を測る
相関係数 (correlation coefficient) = xyの共分散 / (xの標準偏差)(yの標準偏差)
2つの確率変数の間の関係を図る指標
DAU は定義から
売上と因果関係
にもかからず中程度の相関
31
32. 基本KPI: ARPPU
日付、ユーザー別売上
さらに平均を求める
SELECT
DATE(purchase_dt) AS Dt,
user_id,
SUM(unit_price) AS Uriage
FROM tbl_receipt
GROUP BY Dt, user_id
ORDER BY Dt
SELECT
T.Dt AS Date,
FLOOR(AVG(T.Uriage)) AS ARPPU
FROM (
SELECT
DATE(purchase_dt) AS Dt,
user_id,
SUM(unit_price) AS Uriage
FROM tbl_receipt
GROUP BY Dt,user_id
ORDER BY Dt
) AS T
GROUP BY Date
32
43. 43
課金ランキングとプレイ期間から
プレイ中の平均日次課金額
課金ユーザーのプレイ期間
ユーザー毎
総課金額、ランキング順
SELECT
FLOOR(Sougaku / period) AS DRPU
FROM (
SELECT
user_id,
SUM(unit_price) as Sougaku
FROM tbl_receipt
GROUP BY user_id
ORDER BY Sougaku DESC) AS S
INNER JOIN (
SELECT
u.user_id as id,
DATEDIFF(last_login, first_login) as period
FROM user_login AS u
INNER JOIN (
SELECT DISTINCT user_id FROM tbl_receipt) AS r
ON u.user_id = r.user_id
WHERE DATEDIFF(last_login, first_login) > 0) AS P
ON S.user_id = P.id