イベントの説明
要旨
今回のイベントでは、Quantopian Inc.のデータサイエンティストかつPyMC3の開発者であるThomas Wiecki氏をお招きして、「Bayesian Decision Making and PyMC3」という表題でトークして頂きます。
- 参加者の皆様のトークを募集します。長さは5分〜1時間以内で任意です。
- Meetupの終了後、希望者で夕食に行こうと思います。事前にお知らせ頂ければ有り難いです。連絡先はPyData-JP(https://pydata-jp.herokuapp.com/ )のosakaチャネル、またはTaku YoshiokaへのDMでよろしくお願いいたします。
開催日時
2019/10/19(土)
- 15:10 受付開始
- 15:40 開始
場所
京都SBL会議室 大会議室 (https://sblkarasuma.resv.jp/support/support_shop.php)
- 京都地下鉄四条駅より徒歩七分
タイムテーブル
時間 | 内容 | 発表者 |
---|---|---|
15:10 - 15:40 | 受付 | |
15:40 - 15:50 | 開始挨拶、PyData Osakaの紹介 | 吉岡琢 |
15:50 - 16:50 | Impacting the Bottom Line with Bayesian Decision Making and PyMC3 | Thomas Wiecki |
16:55 - 17:05 | スポンサー紹介 | 吉岡琢 |
17:05 - 17:30 | Sinkhorn algorithm and its application | Taku Yoshioka |
17:50 | 閉会 |
Talk: Impacting the Bottom Line with Bayesian Decision Making and PyMC3, Thomas Wiecki, Quantopian Inc.
There are often high expectations on the business impact that data science can produce. Unfortunately, various barriers often hinder the full realization of that impact, starting with communication challenges between different parts of the organization with different backgrounds. To bridge this chasm, data scientists and stake-holders should agree on a business relevant loss function to optimize. This way, any improvements in the model can directly be measured in their impact on the bottom line. In this talk, I will show how probabilistic programming frameworks like PyMC3 can be used to solve applied problems with examples from supply chain management and capital allocation. This approach allows us to accurately and flexibly map a real-world problem to a statistical model that can be quickly iterated and improved on. I will then show how the results of such a model, which are usually arcane and non-actionable posterior probability distributions, can be coupled with a loss function based on business mechanics, to (i) derive business related outcome measures, and (ii) suggest the optimal decision to make, rather than inform it.
スポンサー
Laboro. AI, Inc. (https://laboro.ai)