Muutke küpsiste eelistusi

E-raamat: Demand Prediction in Retail: A Practical Guide to Leverage Data and Predictive Analytics

, , ,
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 74,09 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Demand Prediction in Retail: A Practical Guide to Leverage Data and Predictive AnalyticsSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

From data collection to evaluation and visualization of prediction results, this book provides a comprehensive overview of the process of predicting demand for retailers. Each step is illustrated with the relevant code and implementation details to demystify how historical data can be leveraged to predict future demand. The tools and methods presented can be applied to most retail settings, both online and brick-and-mortar, such as fashion, electronics, groceries, and furniture.





This book is intended to help students in business analytics and data scientists better master how to leverage data for predicting demand in retail applications. It can also be used as a guide for supply chain practitioners who are interested in predicting demand. It enables readers to understand how to leverage data to predict future demand, how to clean and pre-process the data to make it suitable for predictive analytics, what the common caveats are in terms of implementation and how to assess prediction accuracy.
1 Introduction
1(12)
1.1 Motivation
1(2)
1.2 Dataset
3(6)
1.3 Objective and Scope
9(3)
1.3.1 Training and Test Data
9(1)
1.3.2 Prediction Accuracy Metrics
10(1)
1.3.3 Application
11(1)
References
12(1)
2 Data Pre-Processing and Modeling Factors
13(16)
2.1 Dealing with Missing Data
13(4)
2.2 Testing for Outliers
17(1)
2.3 Accounting for Time Effects
18(4)
2.4 Price and Lag-Prices
22(2)
2.5 Featured on Main Page
24(1)
2.6 Item Descriptive Features
25(1)
2.7 Additional Features
25(1)
2.8 Scaling
26(1)
2.9 Sorting and Exporting the Dataset
27(1)
References
27(2)
3 Common Demand Prediction Methods
29(40)
3.1 Primer: Basic Linear Regression for One SKU
30(2)
3.2 Structuring the Dataset
32(1)
3.3 Centralized Approach
33(1)
3.4 Decentralized Approach
34(2)
3.5 Feature Selection and Regularization
36(13)
3.5.1 Subset Selection
36(6)
3.5.2 Lasso Regularization
42(4)
3.5.3 Ridge Regularization
46(1)
3.5.4 Elastic Net Regularization
47(2)
3.6 Log Transformations
49(7)
3.6.1 Log-Transformation on the Price Variable
49(3)
3.6.2 Log-Transformation on the Target Variable
52(2)
3.6.3 Transformations and Prediction Accuracy
54(2)
3.7 Centralized Approach with SKU-Fixed Effects
56(3)
3.8 Centralized Approach with Price-Fixed Effects
59(3)
3.9 Centralized Approach with SKU-Price-Fixed Effects
62(2)
3.10 Decentralized Approach with Aggregated Seasonality
64(2)
3.11 Summary and Next Steps
66(1)
References
67(2)
4 Tree-Based Methods
69(24)
4.1 Decision Tree
70(11)
4.1.1 Centralized Decision Tree
71(8)
4.1.2 Decentralized Decision Tree
79(2)
4.2 Random Forest
81(5)
4.2.1 Centralized Random Forest
82(2)
4.2.2 Decentralized Random Forest
84(2)
4.3 Gradient-Boosted Tree
86(6)
4.3.1 Centralized Gradient Boosted Tree
87(2)
4.3.2 Decentralized Gradient-Boosted Tree
89(3)
4.4 Methods Comparison
92(1)
References
92(1)
5 Clustering Techniques
93(22)
5.1 K-means Clustering
93(10)
5.1.1 Description of K-means Clustering
93(4)
5.1.2 Clustering using Average Price and Weekly Sales
97(3)
5.1.3 Adding Standard Deviations of the Clustering Features
100(3)
5.2 DBSCAN Clustering
103(11)
5.2.1 Description of DBSCAN Clustering
103(5)
5.2.2 Clustering using Average Price and Weekly Sales
108(5)
5.2.3 Adding the Standard Deviation of the Clustering Features
113(1)
References
114(1)
6 Evaluation and Visualization
115(14)
6.1 Summary of Results
115(3)
6.2 Prediction vs. Actual
118(5)
6.3 Varying the Split Ratio
123(6)
7 More Advanced Methods
129(22)
7.1 The Prophet Method
129(14)
7.1.1 What is the Prophet Method?
129(6)
7.1.2 Forecasting with Prophet
135(8)
7.2 Data Aggregation and Demand Prediction
143(6)
7.2.1 Presentation of the DAC Method
143(3)
7.2.2 Fine-Tuning the Hyperparameters
146(1)
7.2.3 Interpretating the DAC Results
147(2)
References
149(2)
8 Conclusion and Advanced Topics
151
References
155
Maxime C. Cohen is a Professor of Retail and Operations Management, Co-Director of the Retail Innovation Lab, and a Bensadoun Faculty Scholar at McGill University, Canada. He is also a Scientific Advisor on AI and Data Science at IVADO Labs and a Scientific Director at the non-profit MyOpenCourt.org. His core expertise lies at the intersection of data science and operations research. He holds a Ph.D. in Operations Research from MIT, USA.

 Paul-Emile Gras is a data scientist at Virtuo Technologies in Paris, France. His expertise is at the interface of demand forecasting and revenue management. Prior to joining Virtuo, he was a research assistant in operations at McGill University, Canada.

 Arthur Pentecoste is a data scientist at the Boston Consulting Groups New York office, USA. His main scope of expertise is in predictive modelling and analytics applied to demand forecasting and predictive maintenance.

 Renyu Zhang is an Assistant Professor of Operations Management at New York University Shanghai, China. He is also an economist and tech lead at Kuaishou, one of the worlds largest online video-sharing and live-streaming platforms. He is an expert on data science and operations research. He holds a Ph.D. in Operations Management from Washington University in St. Louis, USA.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97830308585512e.html
Märksõnad: