Fill in missing data due to web tool omission

docs/AI_Prediction_Result.md

@@ -4,26 +4,26 @@ Analyzing lottery numbers in Python for potential patterns involves collecting h
 
 ### 1. Data Collection and Preprocessing
 
-Web Scraping: Use libraries like and to scrape historical winning numbers from official lottery websites.
-Data Structuring: Store data in a DataFrame, with columns representing the drawing date and the numbers drawn.
-Cleaning: Remove non-numeric characters, handle missing values, and ensure numbers are sorted for consistency. [2, 5, 7]
+- Web Scraping: Use libraries like BeautifulSoup and Selenium to scrape historical winning numbers from official lottery websites.
+- Data Structuring: Store data in a DataFrame, with columns representing the drawing date and the numbers drawn.
+- Cleaning: Remove non-numeric characters, handle missing values, and ensure numbers are sorted for consistency. [2, 5, 7]
 
 ### 2. Statistical Analysis and Pattern Recognition
 
-Frequency Analysis: Calculate how often each number appears to identify "hot" (frequent) and "cold" (infrequent) numbers using .
-Pair/Triplet Frequency: Analyze the frequency of pairs or triplets of numbers appearing together.
-Odd/Even & High/Low Analysis: Determine the distribution of odd/even and high/low numbers to see if specific combinations are more likely. [2, 3, 5, 8, 9]
+- Frequency Analysis: Calculate how often each number appears to identify "hot" (frequent) and "cold" (infrequent) numbers using .
+- Pair/Triplet Frequency: Analyze the frequency of pairs or triplets of numbers appearing together.
+- Odd/Even & High/Low Analysis: Determine the distribution of odd/even and high/low numbers to see if specific combinations are more likely. [2, 3, 5, 8, 9]
 
 ### 3. Predictive Modeling with Python
 
-Machine Learning (Random Forest): Use libraries like to train a on past data to predict the next set of numbers.
-Markov Chains: Model the sequence of numbers to understand transition probabilities (e.g., the likelihood of a specific number following another).
-LSTM Neural Networks: Utilize or to build models, which are effective at analyzing time-series data like lottery draws. [4, 6, 10, 11]
+- Machine Learning (Random Forest): Use libraries like scikit-learn to train on past data to predict the next set of numbers.
+- Markov Chains: Model the sequence of numbers to understand transition probabilities (e.g., the likelihood of a specific number following another).
+- LSTM Neural Networks: Utilize PyTorch or TensorFlow/Keras to build models, which are effective at analyzing time-series data like lottery draws. [4, 6, 10, 11]
 
 ### 4. Simulation and Validation
 
-Simulation: Simulate thousands of draws using to understand the distribution of outcomes.
-Backtesting: Test your model against historical data to evaluate its performance (e.g., checking how many hits a model would have achieved). [3, 6, 10, 12]
+- Simulation: Simulate thousands of draws using to understand the distribution of outcomes.
+- Backtesting: Test your model against historical data to evaluate its performance (e.g., checking how many hits a model would have achieved). [3, 6, 10, 12]
 
 ** Important Note: Lottery draws are designed to be random, and past performance does not guarantee future results. These methods identify historical patterns but cannot predict truly random future outcomes. [3, 8] **