最近因为工作原因需要调研下kaggle比赛《Corporación Favorita Grocery Sales Forecasting》top方案的特征和模型工作,可以借鉴并应用到实际业务中。很多时候我们的任务可能与kaggle中某个比赛是类似的,想又快又好的完成目标其中一条有效的方法就是参考大牛分享的方案。因为很多大牛在比赛打完之后会分享自己的源码,这样相比于...
Xtest, _ = create_dataset(df, promo_df, items, stores, timesteps, date(2017, 8, 16), aux_as_tensor=True, is_train=False, reshape_output=2) 其中函数train_generator: create_dataset_part负责生产一个时间窗的数据 train_generator负责惰性生产多时间窗抽样数据,其中循环一次: 将会随机从样本中抽取...
方案概览: 【Kaggle】Favorita Grocery Sales Forecasting 5th 从源码到方案解读--概览 1.包,其中utils为自编工具from datetime import date, timedelta import pandas as pd import numpy as np from sklearn.m…
This paper is to investigate on comparison between the traditional statistical method models which are ARMA, ARIMA, and ARIMAX model using the dataset provided in Kaggle competition webpage. Three numbers of time series were implemented on the validation, and comparison is done in terms of ...
Paper tables with annotated results for From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba
"Time_series" is the subsequent notebook, where various modeling techniques for time series forecasting have been explored. DATA DESCRIPTION The dataset obtained from Kaggle presents a public collection of Brazilian ecommerce orders conducted at Olist Store. Covering 100,000 orders spanning the period...
storieswithsiva / Kaggle-Predicting-Future-Sales Star 4 Code Issues Pull requests 📈Forecasting Total amount of Products using time-series dataset consisting of daily sales data provided by one of the largest Russian software firms📆 python sales data-science data-mining shop data-visualization...
Furthermore, we used eXtreme Gradient Boosting (XGBoost) to utilize these features for forecasting the future sales amount. The experiment results on a publicly Walmart retail goods dataset provide by Kaggle competition demonstrate our proposed model performs extremely well for sales prediction with ...
该比赛kaggle地址如下: https://www.kaggle.com/c/favorita-grocery-sales-forecasting/overview 整体来看该比赛就是预测商品的销量,官方提供了2013-2017年各商店商品的销量,参赛队伍需要根据已有数据预测未来一段时间商店商品的销量,下面是每年的训练样本量:
简介竞赛简介 https://www.kaggle.com/competitions/favorita-grocery-sales-forecasting/overview数据集也可在竞赛页面下载 代码下载地址 https://www.kaggle.com/code/shixw125/1st-place-lgb-model-public-0-50…