Skip to content
View KT-888's full-sized avatar

Block or report KT-888

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
KT-888/README.md

KT-888 | Data Analyst / Forecasting Engineer

👋 About Me / 自己紹介

I am a data analyst with professional experience in the financial industry.
I hold a CMA (Certified Member Analyst) qualification and specialize in time series forecasting, demand prediction, and EDA.

🔧 Skills / スキル

Category Tools
Language Python
ML Model LightGBM, Prophet, XGBoost
Analysis Time Series, EDA, Feature Engineering, Stock Price Prediction
Data POS Data, Mobile Location Data, Financial Data
Libs pandas, numpy, matplotlib, seaborn, scikit-learn, lightgbm, xgboost, prophet

📂 Featured Projects / 主なプロジェクト

  • Kaggle M5 Forcasting 予測データセットを用いた実務向け予測パイプライン
  • LightGBM + Optuna + Walkforward Validation を用いた、店舗×商品の時系列予測
  • Kaggle Rossmann Store Salesデータを用いた需要予測
  • Expanding Window CVによるデータリークのない検証
  • ベースライン比 64.1%改善(MASE: 0.359)
  • 時系列データの探索的分析(EDA)サンプル
  • ACF/PACF・STL分解・ADF検定まで網羅

💼 Background / 経歴

  • 金融機関での実務経験(証券アナリスト資格保有)
  • POSデータ・携帯位置情報を活用した予測モデル開発経験
  • Python(pandas, LightGBM, Prophet)による時系列分析

Popular repositories Loading

  1. prophet_demand_forecast prophet_demand_forecast Public

    Python + Prophet での需要予測サンプル カレンダーやラグなどを考慮

    Jupyter Notebook

  2. lightgbm_demand_forecast lightgbm_demand_forecast Public

    LightGBMによる需要予測サンプル カレンダー、ラグ、プロモーションや在庫を考慮

    Jupyter Notebook

  3. time_series_eda_demand_forecast time_series_eda_demand_forecast Public

    需要予測のための時系列EDA(探索的データ分析)

    Jupyter Notebook

  4. rossmann-sales-forecasting-lightgbm rossmann-sales-forecasting-lightgbm Public

    LightGBMによる時系列売上予測(Rossmann Store Salesデータ・単店舗分析)

    Jupyter Notebook

  5. KT-888 KT-888 Public

  6. M5-Demand-Forecasting-Pipeline M5-Demand-Forecasting-Pipeline Public

    M5 Forecasting データセットを用いた 実務向け需要予測パイプラインです。

    Python