2016/10/11 Data Analysis Job in Sinica

過完雙十連假，開始了我在中研院進行資料分析的工作，原本對於程式是完全陌生的
偶然在網路上看到了資料科學的文章，也體認到未來資料科學的趨勢，決心要踏入這個領域，很高興能有機會以一個非本科系的身分來到中研院資訊所學習，感覺要學的東西非常多，希望自己能夠堅持住，努力往自己的目標邁進，加油~

楊証琨 2016/10/11

今天閱讀重點

how should people approach problems in data science competitions ?

Let me put it down in 9 basic steps:

1. Understand the problem / objective you are trying to solve.(了解問題，確定目標)
2. Understand and summarize what data you have / need.(了解並統整現有資料)
3. Carefully read about the evaluation metric.(了解評估準則)
4. Explore and visualize the data, build simple, base models for benchmark.(探索分析，建立簡單模型)
5. Setup a robust / thorough validation framework consistent with the evaluation conditions.(建立評估準則)
6. Work on feature engineering and optimizing algorithms.(最佳化演算法)
7. Try out as many different models / ideas as you can.(嘗試不同模型)
8. Ensemble / Blend / Stack multiple models.(混合或堆疊模型)
9. Never hesitate in asking questions, taking help or even teaming up with others(討論不同意見)