Description

This dataset, titled "Cryptocurrency Market Sentiment & Prediction," is a synthetic collection of real-time crypto market data designed for advanced analysis and predictive modeling. It captures a comprehensive range of features including price movements, social sentiment, news impact, and trading patterns for 10 major cryptocurrencies. Tailored for data scientists and analysts, this dataset is ideal for exploring market volatility, sentiment analysis, and price prediction, particularly in the context of significant events like the Bitcoin halving in 2024 and increasing institutional adoption.

Key Features Overview: - Price Movements: Tracks current prices and 24-hour price change percentages to reflect market dynamics. - Social Sentiment: Measures sentiment scores from social media platforms, ranging from -1 (negative) to 1 (positive), to gauge public perception. - News Sentiment and Impact: Evaluates sentiment from news sources and quantifies their potential impact on market behavior. - Trading Patterns: Includes data on 24-hour trading volumes and market capitalization, crucial for understanding market activity. - Technical Indicators: Features metrics like the Relative Strength Index (RSI), volatility index, and fear/greed index for in-depth technical analysis. - Prediction Confidence: Provides a confidence score for predictive models, aiding in assessing forecast reliability.

Purpose and Applications: - Perfect for machine learning tasks such as price prediction, sentiment-price correlation studies, and volatility classification. - Supports time series analysis for forecasting price movements and identifying volatility clusters. - Valuable for research into the influence of social media and news on cryptocurrency markets, especially during high-impact events.

Dataset Scope: - Covers a simulated 30-day period, offering a snapshot of market behavior under varying conditions. - Focuses on major cryptocurrencies including Bitcoin, Ethereum, Cardano, Solana, and others, ensuring relevance to current market trends.

Dataset Structure Table:

Dataset Statistics Table:

This dataset is a powerful resource for machine learning projects, sentiment analysis, and crypto market research, providing a robust foundation for AI/ML model development and testing.

Consumers from countries in Africa, Asia, and South America were most likely to be an owner of cryptocurrencies, such as Bitcoin, in 2025. This conclusion can be reached after combining ** different surveys from the Statista's Consumer Insights over the course of that year. Nearly one out of three respondents to Statista's survey in Nigeria, for instance, mentioned they either owned or use a digital coin, rather than *** out of 100 respondents in the United States. This is a significant change from a list that looks at the Bitcoin (BTC) trading volume in ** countries: There, the United States and Russia were said to have traded the highest amounts of this particular virtual coin. Nevertheless, African and Latin American countries are noticeable entries in that list too. Daily use, or an investment tool? The survey asked whether consumers either owned or used cryptocurrencies but does not specify their exact use or purpose. Some countries, however, are more likely to use digital currencies on a day-to-day basis. Nigeria increasingly uses mobile money operations to either pay in stores or to send money to family and friends. Polish consumers could buy several types of products with a cryptocurrency in 2019. Opposed to this is the country of Vietnam: Here, the use of Bitcoin and other cryptocurrencies as a payment method is forbidden. Owning some form of cryptocurrency in Vietnam as an investment is allowed, however. Which countries are more likely to invest in cryptocurrencies? Professional investors looking for a cryptocurrency-themed ETF were more often found in Europe than in the United or China, according to a survey in early 2020. Most of the largest crypto hedge fund managers with a location in Europe in 2020, were either from the United Kingdom or Switzerland - the country with the highest cryptocurrency adoption rate in Europe according to Statista's Global Consumer Survey. Whether this had changed by 2025 was not yet clear.

«Datasets per la comparació de moviments i patrons entre els principals índexs borsatils espanyols i les crypto-monedes»

Context

En aquest cas el context és detectar o preveure els diferents moviments que es produeixen per una serie factors, tant de moviment interns (compra-venda), com externs (moviments polítics, econòmics, etc...), en els principals índexs borsatils espanyols i de les crypto-monedes.

Hem seleccionat diferents fonts de dades per generar fitxers «csv», guardar diferents valors en el mateix període de temps. És important destacar que ens interessa més les tendències alcistes o baixes, que podem calcular o recuperar en aquests períodes de temps.

Content

En aquest cas el contingut està format per diferents csv, especialment tenim els fitxers de moviments de cryptomoneda, els quals s’ha generat un fitxer per dia del període de temps estudiat.

Pel que fa als moviments del principals índexs borsatils s’ha generat una carpeta per dia del període, en cada directori un fitxer amb cadascun del noms dels índexs. Degut això s’han comprimit aquests últims abans de publicar-los en el directori de «open data» kaggle.com.

Pel que fa als camps, ens interessà detectar els moviments alcistes i baixistes, o almenys aquelles que tenen un patró similar en les cryptomonedes i els índexs. Els camps especialment destacats són:

• Data: Data de la observació
• Nom: Nom empresa o cryptomoneda, per identificar de quina moneda o index estem representant.
• Símbol: Símbol de la moneda o del index borsatil, per realitzar gràfic posteriorment d’una forma mes senzilla que el nom.
• Preu: Valor en euros d’una acció o una cryptomoneda (transformarem la moneda a euros en el cas de estigui en dòlars amb l'última cotització (un dollar a 0,8501 euro)
• Tipus_cotitzacio: Valor nou que agregarem per discretitzar entre la cotització: baix (0 i 1), normal (1 i 100), alt (100 i 1000), molt_alt (>1000)

Acknowledgements

En aquest cas les fonts de dades que s’han utilitzat per a la realització dels datasets corresponent a:

• http://www.eleconomista.es
• https://coinmarketcap.com

Per aquest fet, les dades de borsa i crypto-moneda estan en última instància sota llicència de les webs respectivament. Pel que fa a la terminologia financera podem veure vocabulari en renta4banco.
[https://www.r4.com/que-necesitas/formacion/diccionario]

Inspiration

Hi ha un estudi anterior on poder tenir primícies de com han enfocat els algoritmes:

• https://arxiv.org/pdf/1410.1231v1.pdf

En aquest cas el «trading» en cryptomoneda és relativament nou, força popular per la seva formulació com a mitja digital d’intercanvi, utilitzant un protocol que garanteix la seguretat, integritat i equilibri del seu estat de compte per mitjà d’un entramat d’agents.

La comunitat podrà respondre, entre altres preguntes, a:

• Està afectant o hi ha patrons comuns en les cotitzacions de cryptomonedes i el mercat de valors principals del país d'Espanya?
• Els efectes o agents externs afecten per igual a les accions o cryptomonedes?
• Hi ha relacions cause efecte entre les acciones i cryptomonedes?

Project repository

https://github.com/acostasg/scraping

Datasets

Els fitxers csv generats que componen el dataset s’han publicat en el repositori kaggle.com:

• https://www.kaggle.com/acostasg/stock-index/
• https://www.kaggle.com/acostasg/crypto-currencies

Per una banda, els fitxers els «stock-index» estan comprimits per carpetes amb la data d’extracció i cada fitxer amb el nom dels índexs borsatil. De forma diferent, les cryptomonedes aquestes estan dividides per fitxer on són totes les monedes amb la data d’extracció.

In 2024, a country ranking that estimates crypto adoption based on transaction volume placed Malaysia in the top 50 in the world. Moreover, Malaysia was in the **** place based on its P2P exchange trade volume. Peer-to-peer (P2P) crypto exchanges are a type of crypto exchange that let users trade cryptocurrencies with one another without the influence of a mediator, such as banks or other regulatory bodies.

Cryptocurrency historical datasets from January 2012 (if available) to October 2021 were obtained and integrated from various sources and Application Programming Interfaces (APIs) including Yahoo Finance, Cryptodownload, CoinMarketCap, various Kaggle datasets, and multiple APIs. While these datasets used various formats of time (e.g., minutes, hours, days), in order to integrate the datasets days format was used for in this research study. The integrated cryptocurrency historical datasets for 80 cryptocurrencies including but not limited to Bitcoin (BTC), Ethereum (ETH), Binance Coin (BNB), Cardano (ADA), Tether (USDT), Ripple (XRP), Solana (SOL), Polkadot (DOT), USD Coin (USDC), Dogecoin (DOGE), Tron (TRX), Bitcoin Cash (BCH), Litecoin (LTC), EOS (EOS), Cosmos (ATOM), Stellar (XLM), Wrapped Bitcoin (WBTC), Uniswap (UNI), Terra (LUNA), SHIBA INU (SHIB), and 60 more cryptocurrencies were uploaded in this online Mendeley data repository. Although the primary attribute of including the mentioned cryptocurrencies was the Market Capitalization, a subject matter expert i.e., a professional trader has also guided the initial selection of the cryptocurrencies by analyzing various indicators such as Relative Strength Index (RSI), Moving Average Convergence/Divergence (MACD), MYC Signals, Bollinger Bands, Fibonacci Retracement, Stochastic Oscillator and Ichimoku Cloud. The primary features of this dataset that were used as the decision-making criteria of the CLUS-MCDA II approach are Timestamps, Open, High, Low, Closed, Volume (Currency), % Change (7 days and 24 hours), Market Cap and Weighted Price values. The available excel and CSV files in this data set are just part of the integrated data and other databases, datasets and API References that was used in this study are as follows: [1] https://finance.yahoo.com/ [2] https://coinmarketcap.com/historical/ [3] https://cryptodatadownload.com/ [4] https://kaggle.com/philmohun/cryptocurrency-financial-data [5] https://kaggle.com/deepshah16/meme-cryptocurrency-historical-data [6] https://kaggle.com/sudalairajkumar/cryptocurrencypricehistory [7] https://min-api.cryptocompare.com/data/price?fsym=BTC&tsyms=USD [8] https://min-api.cryptocompare.com/ [9] https://p.nomics.com/cryptocurrency-bitcoin-api [10] https://www.coinapi.io/ [11] https://www.coingecko.com/en/api [12] https://cryptowat.ch/ [13] https://www.alphavantage.co/ This dataset is part of the CLUS-MCDA (Cluster analysis for improving Multiple Criteria Decision Analysis) and CLUS-MCDAII Project: https://aimaghsoodi.github.io/CLUSMCDA-R-Package/ https://github.com/Aimaghsoodi/CLUS-MCDA-II https://github.com/azadkavian/CLUS-MCDA

This dataset appears to be a time series dataset containing financial market data, specifically related to a certain asset or cryptocurrency. The columns in the dataset represent various financial metrics and market attributes. Here's a brief description of each column:

Date (Start-End): This column likely represents the time period for which the data is recorded, with a start and end date for each entry.

Open: The opening price of the asset or cryptocurrency at the beginning of the time period.

High: The highest price reached during the time period.

Low: The lowest price reached during the time period.

Close: The closing price of the asset or cryptocurrency at the end of the time period.

Volume: The trading volume, which typically represents the total number of units of the asset traded during the time period.

Market Cap: The market capitalization, which is often the product of the closing price and the total supply of the asset.

This dataset can be used for various financial and statistical analyses, including studying price trends, volatility, and trading volume over time. It may be particularly useful for analyzing the performance of the asset or cryptocurrency over the given time frame and identifying patterns or insights for investment or trading strategies.

The dataset consists in cryptocurrency prices, sp500, epu and google trends statistics at daily frequency, as well as the matlab codes used for the analyses.

In 2024, a country ranking that estimated crypto adoption based on transaction volume placed Indonesia in the top ***** of the world. Indonesia ranked ***** in the world when it comes to retail value received from DeFi protocols or consumers who were buying certain DeFi protocols.

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

Visa (V) Stock: Will Digital Currency Overtake Physical?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

Will the S&P Bitcoin Index Revolutionize Cryptocurrency?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

The United Kingdom was believed to be in the top ** countries in the world in 2022 regarding crypto adoption. This is according to a model based on website traffic patterns from individual websites used for cryptocurrency transactions. The UK ranks consistently in the top ** throughout the years under consideration, although its P2P activities - ranked at position ** in 2023 - seem to lower its global ranking when compared to countries from Asia.

Graph and download economic data for Nasdaq Brazil Bitcoin Futures TR Index (NASDAQNQBTCBRT) from 2025-06-27 to 2025-08-07 about cryptocurrency, NASDAQ, Brazil, indexes, and USA.

Graph and download economic data for Coinbase Index (DISCONTINUED) from 2015-01-01 to 2020-05-26 about cryptocurrency, indexes, and USA.

In the context of the COVID-19’s outbreak and its implications for the financial sector, this study analyses the aspect of hedging and safe-haven under pandemic. Drawing on the daily data from 02 August 2019 to 17 April 2020, our key findings suggest that the contagious effects in financial assets’ returns significantly increased under COVID-19, indicating exacerbated market risk. The connectedness spiked in the middle of March, consistent with lockdown timings in major economies. The effect became severe with the WHO’s declaration of a pandemic, confirming negative news effects. The return connectedness suggests that COVID-19 has been a catalyst of contagious effects on the financial markets. The crude oil and the government bonds are however not as much affected by the spillovers as their endogenous innovation. In term of spillovers, we do find the safe-haven function of Gold and Bitcoin. Comparatively, the safe-haven effectiveness of Bitcoin is unstable over the pandemic. Whereas, GOLD is the most promising hedge and safe-haven asset, as it remains robust during the current crisis of COVID-19 and thus exhibits superiority over Bitcoin and Tether. Our findings are useful for investors, portfolio managers and policymakers interested in spillovers and safe havens during the current pandemic.

Crypto Trading and Technical Indicators

Understanding the Market Dynamics of 600 Popular Cryptocurrencies

By [source]

About this dataset

This dataset provides an unprecedented overview of the crypto industry, offering comprehensive market analysis of more than 600 well-known cryptocurrencies. The data contained in this dataset is extremely up-to-date, ranging from trading statuses, price movements and volatility levels to technical indicators and market capitalization. Perfect for those interested in cryptocurrency trading, technical analysis or investing, this data can be used to facilitate informed decisions and fulfill respective requirements.
The 35 columns present in this dataset enable users to gain a greater understanding into price movements and distinguish between various levels of volatility. It also allows users to analyze oscillator ratings for each crypto asset listed within for accurate risk management. Banks, investors, data analysts as well as crypto exchanges could all benefit from utilizing this powerful dataset; its ability to provide a top level summary into the entire crypto industry has earned it a valuable place among the cryptocurrency community worldwide

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset provides comprehensive market analysis of more than 600 popular cryptocurrencies, including trading prices, volatility, technical indicators, and market capitalization. In this guide, we'll cover what kind of information you can obtain from the dataset, how to use it effectively to gain insight into the crypto industry, and how to analyze the results in order to make informed decisions regarding cryptocurrency trading.

The dataset consists of 35 columns that are divided into two main categories: Market Information and Technical Indicators. The Market Information section contains data about each cryptocurrency's price performance – including change percentages for 1 week/1 month/3 months/6 months/1 year – as well as its fully diluted market capitalization (FD Mkt Cap), traded volume (Traded Vol), last trading price in USD (Last_y), available coins (Avail Coins), total coins created with a max supply(Total Coins) and its respective rating out of 5 stars by moving averages(Moving Averages Rating). The Technical Indicators section includes data pertaining to oscillator ratings (Oscillators Rating) such as Average Directional Index (ADX), Awesome Oscillator(AO), Average True Range(ATR) , Commodity Channel Index20(CCI20) etc., moving averages such as Simple Moving Average 20 days /50 days / 200 days (SMA20/ SMA50 / SMA200) , Bollinger Bands upper & lower limit lines comprised of standard deviations known as BB Up & BB Low respectively , Momentum(MOM ), Relative Strength Index14 day time frame indicator denoted by RSI14 , Macd level & signal line along with Stochitic %K &%D indicators.

With all that knowledge now let’s take a look at some tips on how you can analyse this data effectively. For example: finding safety ranks based on volatility scores or locatingcryptocurrencies whose MACD line has recently crossed over its signal line thus giving buy signals or vice versa giving sell signals also mining through various time frames using multiple technical indicators like ADX +CCI20+RSI14 etc can help spot potential trends which may be indicative for a particular currency . Also moving averages assessments over several time periods might be useful for calculating trend based values in order for possible bullish or bearish orientations . Furthermore when examining long term trends across multiple currencies it might be suitable carry out simple comparisons between certain columns from one currency against

Research Ideas

• Utilizing the price movements and technical indicators, investors can analyze the different crypto industry trends and develop strategies to apply them in their portfolios.
• Governmental institutions and banks can use this dataset to monitor the industry’s activity from country to country, helping create regulatory policies when necessary.
• Crypto exchanges can design algorithms based on this data set which will assist with detecting any manipulation or malicious activities in trades occurring in their platform

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication No Copyright - Y...

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

Will the S&P Bitcoin Index Usher in a New Era for Cryptocurrency?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

India ranked as the main country worldwide in terms of how far developed its retail Central Bank Digital Currencies (CBDC) were, as of November 2023. This is according to a top 10 that is released once every year, tracking the development of CBDC across countries based on a development index - with India's index value of ** outranking those of Ukraine and Thailand. In earlier years, China, Nigeria and the Eastern Caribbean show up. The source left these out in the 2023 release, however, as these coins were already live or very close to being live. Note that the figures provided here are for retail CBDC, which can be held and used by both consumers and companies as a substitute for paper money or physical coins: Retail CBDC is essentially a digital substitute for fiat currency. This is different from developments found in interbank CBDC - which concerns cryptocurrencies used by financial institutions for interbank payments and financial settlement processes.

Between 2020 and 2023, a country ranking that estimates crypto adoption based on transaction volume consistently placed the U.S. in ********** of the world. The figure for 2022, especially, stands out as it broke a declining trend in 2021 and was likely caused by the change of the methodology to now include Decentralized Finance (DeFi) in the index. For example, the United States ranked second in the world when it comes to on-chain retail value received from DeFi protocols - or consumers who were buying certain DeFi protocols. This may refer to the growing use of OpenSea and other Web3 wallets within the U.S. particularly in the first months of 2022.

The Cryptocurrency research & publication dataset, which was indexed by Scopus from 1984 to 2020. The dataset contains data authors, authors ID Scopus, title, year, source title, volume, issue, article number in Scopus, DOI, link, affiliation, abstract, index keywords, references, Correspondence Address, editors, publisher, conference name, conference date, conference code, ISSN, language, document type, access type, and EID.

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

Will the S&P Bitcoin Index Usher in a New Era of Cryptocurrency Adoption?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data