UID:
edoccha_9961535692702883
Format:
1 online resource (481 pages)
Edition:
First edition.
ISBN:
9783031560972
Series Statement:
International Series in Operations Research and Management Science Series ; Volume 354
Note:
Intro -- Preface -- Acknowledgment -- Contents -- Abbreviations -- Chapter 1: Introduction -- What Is AI? -- Brief History -- Machine Learning -- Deep Learning -- Time Series -- Multivariant Time Series -- Autocorrelation -- Partial Autocorrelation Function (PACF) -- Stationarity Check: Augmented Dickey-Fuller (ADF) and Kwiatkowski-Phillips-Schmidt-Shin (KPSS) Tests -- Non-stationary Stochastic Time Series -- Random Walk Without Drift -- Random Walk with Drift -- Deterministic Trend -- Trend + Cycle -- Random Walk with Drift and Deterministic Trend -- Forecasting Models -- Supervised Learning -- Regression Models -- Metrics for Regression Models -- Ordinary Least Squares Linear Regression -- Mean Squared Errors (MSE) -- Root Mean Squared Error (RMSE) -- Logistic Regression -- Random Forest Trees -- Gradient Boosting Regressor -- Polynomial Regression -- References -- Chapter 2: Natural Language Models -- Potential Use Cases -- NLP Techniques -- Tokenization -- Part-of-Speech (POS) Detection -- Stemming and Lemmatization -- Entity Extraction -- Cosine Similarity Search -- GFS Analytics Framework -- Deep Learning and NLP -- Word Embeddings -- Term Frequency-Inverse Document Frequency (TF-IDF) -- Bag of Words (BOW) -- Economic and Social Sustainability Data Mining Using NLP and Budget Speeches -- Development of Budget Speech Embeddings with Classical NLP -- Building BOW Embedding -- Economic Sustainability BOW Embedding Model -- Data Sources -- Step 1: Load Libraries for Performing NLP -- Step 2: Initialize Memory Variables and NLP Stop Word Processor -- Step 3: Set Tokenizer -- Step 4: Lemmatize and Stem Each Word -- Step 5: Process String -- Step 6: Convert Budget Speech Statements Into Embeddings -- Step 7: Entry Function -- Step 8: Output Budget Speech Statement Word Embeddings -- Step 9: Vector Embedding.
,
Adaptive Machine Learning Model: Automated Budget Statement Labeler -- Chapter Machine Learning Experiments -- References -- Untitled -- Chapter 3: Large Language Models -- What Is AI? -- Brief History -- Machine Learning -- Deep Learning -- Generative AI -- Large Language Foundation Models -- BERT (Bidirectional Encoder Representations from Transformers) -- Large Language Model Meta AI (Llama) -- The Transformer -- Self-Attention in Detail -- Large Language Model: Generate Social Sustainability Strategies with Llama 2 Model -- Step 1: Access -- Step 2: Install the Model and Libraries -- Step 3: Initialize the Model -- Step 4: Initialize Tokenizer -- Step 5: Initialize Tokenizer -- Step 6: Prepare Multiclass Multilabel Prompt Template -- Step 7: Classify the Model -- GPT Models (Generative Pre-trained Transformer) -- Prompt Engineering -- Strategies for Getting Better Results -- How GPT Model Works -- Embeddings -- What Are Embeddings? -- Large Language Model: Generate Social Sustainability Strategies with GPT-2 Model -- Step 1: Install Transformers -- Step 2: Set Output Maximum Length and Seed Value -- Step 3: Generate Social Sustainability Strategies -- Step 4: Choose GPT-2 Large Model -- Step 5: Greedy Search Decoding Method -- Step 6: Beam Search with N-gram Penalties -- Step 6: Basic Sampling -- Step 7: Top-K Sampling -- Step 8: Top-P Sampling -- Step 9: Top-K and Top-P Sampling -- Chain of Thought -- Large Language Model: Economic and Social Sustainability of Marginalized Communities Chat with Indian Union Budget Speeches -- Step 1: Install Transformers -- Step 2: Bring Your Own Budget Speech Files -- Step 3: Recursive Character Text Splitter -- Step 4: Create Local Index Stores to Store Embeddings -- Step 5: Create Chat QA Interface -- Step 6: Prompt Engineering to Retrieve Macroeconomic Stability Statements.
,
Step 7: Prompt Engineering to Retrieve Macroeconomic Stability Statements -- Step 8: Prompt Engineering to Retrieve Economic Sustainability Budget Statements -- Step 9: Prompt Engineering with Few Shots to Classify Economic Sustainability Results -- Step 10: Prompt Engineering to Retrieve Social Sustainability Results -- Step 11: Prompt Engineering with Few Shots to Classify Social Sustainability Results -- References -- Chapter 4: Macroeconomic Indicators, Aggregates, and Framework -- Fiscal and Macroeconomic Stabilization -- Fiscal Discipline -- Fiscal Correction -- Enhancing Credit Delivery -- Machine Learning Model: Money Supply and Economic Growth-SLR, CRR, and BR -- Step 1: Load the Libraries -- Step 2: Load Statutory Liquidity Ratio (SLR) Data -- Step 3: Load Bank Rate Data -- Step 4: Load Bank Credit Data -- Step 5: Load Cash Reserve Data -- Step 6: Merge CRR, SLR, Bank Rate, and Bank Credit -- Step 7: Correlation Analysis -- Step 8: Linear Regressor Model -- Step 8: Evaluate Linear Regressor Model Metrics -- Step 8: Model Explainability -- Step 9: Gradient Boosting Regressor Model -- Step 10: Evaluate Linear Regressor Model Metrics -- Step 11: Model Explainability -- Step 12: Random Forest Regressor -- Conclusions and Policy Implications -- Machine Learning Model: Budget Deficit, Money Supply, and Inflation Linkage and Policy Implications -- Data Sources -- Step 1: Load Libraries for performing Time Series and ML Modeling -- Step 2: Load Broad Money Growth (Annual %), Money Stock, Inflation, GDP, and Deficit Data for India -- Step 3: Check for Nulls in the Data -- Step 4: Correlation Analysis -- Step 5: Plot Dataset -- Step 6: Transformation -- Step 7: Normality Test -- Step 8: Check for Autocorrelation -- Step 10: Train and Test Data -- Step 11: Transformation -- Step 12: Stationarity Check.
,
Step 12: Plot Visualization to See Variables Stationarity -- Step 13: Granger´s Causality Test -- Step 14: VAR Model -- Step 15: Residual Plot -- Conclusion -- Impacts of Financial Development and Other Factors on Inequality and Poverty -- Share Prices -- Inflation -- Imports -- Food Grain Stocks -- Exchange Rate -- Removal of Bureaucratic Interference -- Manufacturing -- Modeling Key Macroeconomic Key Indicators -- UNSD Statistical Yearbook -- OCED Main Economic Indicators -- Statistical Methodological Information for International Comparisons: Dissemination Model -- Main Economic Indicators (MEI) Short-Term Aggregates -- The World Bank Open Data -- Poverty and Inequality -- Economic Indicators -- Gross Savings (% of GDP) -- Chapter Machine Learning Experiments -- References -- Chapter 5: Economic Sustainability -- Industrial Production -- Foreign Investment -- Exports -- The Public Distribution System (PDS) -- Machine Learning Linkage Model: Public Distribution System and Inflation-Protect the Poorer Sections of the Population from Hi... -- Step 1: Load the Libraries -- Step 2: Load Public Distribution System Procurement, Off-Take, and Stocks Data -- Step 3: Load Inflation, Consumer Prices (Annual Percentage) -- Step 4: Load Population Growth (Annual Percentage) Data -- Step 5: Load Poverty Headcount (< -- 1.9) Data -- Step 6: Load Economic and Drought Years Binary Data -- Step 7: Merge Public Distribution System (PDS), Inflation, Poverty Rates, Population Growth, and Recession/Drought Data -- Step 8: Linear Regressive Model -- Step 9: Model Metrics -- Step 10: Model Equation (Y = MX + C) -- Step 11: Model Explainability -- Step 12: Gradient Boosting Regressor Model -- Step 13: Gradient Boosting Regressor Model Metrics -- Step 14: Model Explainability -- Step 15: Random Forest Model -- Step 16: Random Forest Regressor Model Metrics.
,
Step 17: Model Explainability -- Model Comparison and Summary -- Policy Recommendations and Future Consideration -- Machine Learning Modeling-Public Distribution System-Off-Take, a True Indicator of Economic and Social Sustainability (1990:20... -- Coincidence of Recessions with Credit Crunch and Bursts -- Data Sources -- Step 1: Load Libraries for Performing Time Series and ML Modeling -- Step 2: Load Money-Banking, Financial Markets, Public Finances, Trade Balance of Payments Linkage Data for India -- Step 3: Check for Nulls in the Data -- Step 4: Correlation Analysis -- Step 5: Plot Dataset -- Step 6: Transformation -- Step 7: Normality Test -- Step 8: Normality Probability Plot -- Step 9: Check for Autocorrelation -- Step 10: Train and Test Data -- Step 11: Transformation -- Step 12: Stationarity Check -- Step 12: Plot Visualization to See Variables Stationarity -- Step 13: Granger´s Causality Test -- Step 14: VAR Model -- Step 15: Residual Plot -- Step 16: Durbin-Watson Statistics -- Step 17: Prediction or Forecast VAR -- Step 18: Invert the Transformation -- Step 19: Evaluation -- Policy Implication -- Data Science Infused Policy Implications: Large Language Models and Public Services Forecasting Patterns -- Step 1: Prepare Time Series Prophet Model -- Step 2: Prepare Prophet Time Series Variables -- Step 3: Check Any Nulls -- Step 4: Split Data to Model Time Series -- Step 5: Prepare Prophet Time Series Model -- Step: Forecast Model -- Step: Evaluate the Model -- Agricultural Productivity and Prosperity for Farmers -- Agricultural Credit -- Sustainable Farming Practices -- Machine Learning Model: Sustained Agricultural Production and Productivity Enhancement Needs in the Era of Climate Change -- India and Wheat Production -- Indian Wheat Growing Zones -- India and Heat Waves: Wheat Yield Drop -- 2015 Heat Wave in India and Pakistan.
,
2019 Heat Wave in India and Pakistan.
Additional Edition:
Print version: Vuppalapati, Chandrasekar Assessing Policy Effectiveness Using AI and Language Models Cham : Springer,c2024 ISBN 9783031560965
Language:
English
Bookmarklink
