1. Home
  2. Detail

@cm_ae: i had to let her go #peterparker #spidermanbrandnewday #spiderman #mj #spidermanbrandnewdayedit #edit #viral #ae #fy #fypp #foryou #fory #foryourpage #fyp

✤ 𝑚𝑎𝑟𝑖𝑎 ✤
✤ 𝑚𝑎𝑟𝑖𝑎 ✤
Open In TikTok:
Region: GR
Tuesday 06 October 2026 20:46:42 GMT
1228
287
2
9

Music

Download

No Watermark .mp4 (2.06MB) No Watermark(HD) .mp4 (1.58MB) Watermark .mp4 (2.06MB) Music .mp3

Comments

n_no811
愛Nino :
In another life
2026-10-07 10:04:06
1
mariag3172
Maria :
2026-10-06 22:27:11
4
To see more videos from user @cm_ae, please go to the Tikwm homepage.

Other Videos

#কোনোদিন এভাবে #নিজের আপন #মানুষ গুলো #বিদায় #দিবে 😭😭😭
#কোনোদিন এভাবে #নিজের আপন #মানুষ গুলো #বিদায় #দিবে 😭😭😭
🥰🥰🥰
🥰🥰🥰
Fraud detection is not just about building a Machine Learning model. Before training a model, we need to understand the data, identify patterns, and discover what makes fraudulent transactions different from legitimate ones. That process begins with EDA 🚀 🎯 PROJECT OBJECTIVE The goal is to explore credit card transaction data and identify patterns related to: 💳 Transaction Amount ⏱️ Transaction Time 📊 Transaction Frequency 🔍 Fraud vs Legitimate Transactions 🔄 EDA WORKFLOW 1️⃣ UNDERSTAND THE DATA 📂 Explore: 📏 Dataset Shape 📊 Data Types ❓ Missing Values 🔁 Duplicate Transactions 🎯 Target Variable Distribution 2️⃣ ANALYZE FRAUD DISTRIBUTION ⚖️ Compare: ✅ Legitimate Transactions 🚨 Fraudulent Transactions 💡 Fraud datasets are often highly imbalanced, meaning fraudulent transactions may represent only a very small percentage of all transactions. 3️⃣ ANALYZE TRANSACTION AMOUNTS 💰 Investigate: 📈 Average Transaction Amount 📊 Fraud Amount Distribution 🔍 Outliers ⚖️ Fraud vs Legitimate Amounts 4️⃣ EXPLORE TRANSACTION TIME ⏱️ Look for patterns such as: 🌙 Unusual Transaction Hours 📅 Time-Based Trends ⏰ Peak Fraud Periods 🔄 Transaction Frequency 5️⃣ FEATURE CORRELATION 🔗 Analyze relationships between variables using: 📊 Correlation Matrix 🔥 Heatmaps 📈 Distribution Plots 6️⃣ DETECT OUTLIERS 🚨 Identify unusual transactions using: 📦 Box Plots 📊 Histograms 📈 Distribution Analysis ⚠️ Statistical Methods 7️⃣ COMPARE FRAUD VS LEGITIMATE TRANSACTIONS 🔍 Ask important questions: ❓ Are fraudulent transactions larger? ❓ Do fraudsters transact at unusual times? ❓ Are certain features associated with fraud? ❓ Are there unusual patterns in transaction behaviour? 📊 VISUALIZATIONS 📈 Transaction Amount Distribution 📊 Fraud vs Legitimate Count 📦 Box Plot Analysis 🔥 Correlation Heatmap 📉 Feature Distributions ⏱️ Time-Based Analysis 🛠️ TOOLS USED 🐍 Python 🐼 Pandas 🔢 NumPy 📊 Matplotlib ✨ Seaborn 📓 Jupyter Notebook 🚀 NEXT STEP: MACHINE LEARNING After EDA, we can build models such as: 🌳 Random Forest ⚡ XGBoost 🎯 Logistic Regression 🧠 Neural Networks Then evaluate them using: 🎯 Precision 📢 Recall ⚖️ F1-Score 📊 ROC-AUC 💡 In fraud detection, accuracy alone can be misleading. A model that predicts every transaction as legitimate may achieve high accuracy while detecting zero fraud. The real challenge is finding fraudulent transactions while minimizing false alarms. Raw Data → EDA → Feature Engineering → ML Model → Fraud Detection 💳🤖 #FraudDetection #CreditCardFraud #DataScience #EDA #ExploratoryDataAnalysis
Fraud detection is not just about building a Machine Learning model. Before training a model, we need to understand the data, identify patterns, and discover what makes fraudulent transactions different from legitimate ones. That process begins with EDA 🚀 🎯 PROJECT OBJECTIVE The goal is to explore credit card transaction data and identify patterns related to: 💳 Transaction Amount ⏱️ Transaction Time 📊 Transaction Frequency 🔍 Fraud vs Legitimate Transactions 🔄 EDA WORKFLOW 1️⃣ UNDERSTAND THE DATA 📂 Explore: 📏 Dataset Shape 📊 Data Types ❓ Missing Values 🔁 Duplicate Transactions 🎯 Target Variable Distribution 2️⃣ ANALYZE FRAUD DISTRIBUTION ⚖️ Compare: ✅ Legitimate Transactions 🚨 Fraudulent Transactions 💡 Fraud datasets are often highly imbalanced, meaning fraudulent transactions may represent only a very small percentage of all transactions. 3️⃣ ANALYZE TRANSACTION AMOUNTS 💰 Investigate: 📈 Average Transaction Amount 📊 Fraud Amount Distribution 🔍 Outliers ⚖️ Fraud vs Legitimate Amounts 4️⃣ EXPLORE TRANSACTION TIME ⏱️ Look for patterns such as: 🌙 Unusual Transaction Hours 📅 Time-Based Trends ⏰ Peak Fraud Periods 🔄 Transaction Frequency 5️⃣ FEATURE CORRELATION 🔗 Analyze relationships between variables using: 📊 Correlation Matrix 🔥 Heatmaps 📈 Distribution Plots 6️⃣ DETECT OUTLIERS 🚨 Identify unusual transactions using: 📦 Box Plots 📊 Histograms 📈 Distribution Analysis ⚠️ Statistical Methods 7️⃣ COMPARE FRAUD VS LEGITIMATE TRANSACTIONS 🔍 Ask important questions: ❓ Are fraudulent transactions larger? ❓ Do fraudsters transact at unusual times? ❓ Are certain features associated with fraud? ❓ Are there unusual patterns in transaction behaviour? 📊 VISUALIZATIONS 📈 Transaction Amount Distribution 📊 Fraud vs Legitimate Count 📦 Box Plot Analysis 🔥 Correlation Heatmap 📉 Feature Distributions ⏱️ Time-Based Analysis 🛠️ TOOLS USED 🐍 Python 🐼 Pandas 🔢 NumPy 📊 Matplotlib ✨ Seaborn 📓 Jupyter Notebook 🚀 NEXT STEP: MACHINE LEARNING After EDA, we can build models such as: 🌳 Random Forest ⚡ XGBoost 🎯 Logistic Regression 🧠 Neural Networks Then evaluate them using: 🎯 Precision 📢 Recall ⚖️ F1-Score 📊 ROC-AUC 💡 In fraud detection, accuracy alone can be misleading. A model that predicts every transaction as legitimate may achieve high accuracy while detecting zero fraud. The real challenge is finding fraudulent transactions while minimizing false alarms. Raw Data → EDA → Feature Engineering → ML Model → Fraud Detection 💳🤖 #FraudDetection #CreditCardFraud #DataScience #EDA #ExploratoryDataAnalysis
مرکز الحجامه روحانی# دارالشفاء #هلمند #لښکرګاه #واټسف0744718845 #واټسف0705584900 #فیرکفنګ
مرکز الحجامه روحانی# دارالشفاء #هلمند #لښکرګاه #واټسف0744718845 #واټسف0705584900 #فیرکفنګ
Most people learn AI by watching tutorials. The fastest learners also: 📚 Read research papers 🧪 Experiment with models 💻 Study real implementations 🧠 Understand the fundamentals These websites can give you a serious advantage 👇 1️⃣ Papers with Code 📄💻 Find: 📚 Research Papers 💻 Official Implementations 📊 Benchmarks 🤖 State-of-the-Art Models Best for: Connecting AI research with real code. 2️⃣ Hugging Face 🤗 Explore: 🤖 Pretrained Models 📊 Datasets 🧪 Spaces 📚 AI Libraries Best for: Building and experimenting with modern AI applications. 3️⃣ Kaggle 📊 Practice with: 📂 Real Datasets 🏆 Competitions 📓 Notebooks 💬 Community Discussions Best for: Hands-on Data Science and Machine Learning. 4️⃣ arXiv 📚 Read the latest research in: 🧠 Artificial Intelligence 🤖 Machine Learning 👁️ Computer Vision 📝 NLP 🔬 Deep Learning Best for: Staying close to cutting-edge research. 5️⃣ Google Colab ⚡ Build and experiment with: 🐍 Python 🧠 Neural Networks 🤖 Machine Learning Models 🔥 GPU-Accelerated Projects Best for: Practising AI without needing an expensive setup. 🚀 HOW TO USE THEM 📚 Find a paper on arXiv ⬇️ 💻 Check its implementation on Papers with Code ⬇️ 🤗 Find a model or dataset on Hugging Face ⬇️ ⚡ Experiment in Google Colab ⬇️ 🏆 Test your skills on Kaggle That’s a complete AI learning loop. 🔥 💡 The advantage doesn’t come from bookmarking these websites. It comes from actually using them to build, experiment, and understand. Save this list for your AI/ML journey 📌🤖 #AI #MachineLearning #ArtificialIntelligence #creatorsearchinsights #datascience
Most people learn AI by watching tutorials. The fastest learners also: 📚 Read research papers 🧪 Experiment with models 💻 Study real implementations 🧠 Understand the fundamentals These websites can give you a serious advantage 👇 1️⃣ Papers with Code 📄💻 Find: 📚 Research Papers 💻 Official Implementations 📊 Benchmarks 🤖 State-of-the-Art Models Best for: Connecting AI research with real code. 2️⃣ Hugging Face 🤗 Explore: 🤖 Pretrained Models 📊 Datasets 🧪 Spaces 📚 AI Libraries Best for: Building and experimenting with modern AI applications. 3️⃣ Kaggle 📊 Practice with: 📂 Real Datasets 🏆 Competitions 📓 Notebooks 💬 Community Discussions Best for: Hands-on Data Science and Machine Learning. 4️⃣ arXiv 📚 Read the latest research in: 🧠 Artificial Intelligence 🤖 Machine Learning 👁️ Computer Vision 📝 NLP 🔬 Deep Learning Best for: Staying close to cutting-edge research. 5️⃣ Google Colab ⚡ Build and experiment with: 🐍 Python 🧠 Neural Networks 🤖 Machine Learning Models 🔥 GPU-Accelerated Projects Best for: Practising AI without needing an expensive setup. 🚀 HOW TO USE THEM 📚 Find a paper on arXiv ⬇️ 💻 Check its implementation on Papers with Code ⬇️ 🤗 Find a model or dataset on Hugging Face ⬇️ ⚡ Experiment in Google Colab ⬇️ 🏆 Test your skills on Kaggle That’s a complete AI learning loop. 🔥 💡 The advantage doesn’t come from bookmarking these websites. It comes from actually using them to build, experiment, and understand. Save this list for your AI/ML journey 📌🤖 #AI #MachineLearning #ArtificialIntelligence #creatorsearchinsights #datascience
#burakozcivit #tiktok #foryou #tiktokteamplzsupportme #creatorsearchinsights
#burakozcivit #tiktok #foryou #tiktokteamplzsupportme #creatorsearchinsights

About

Legal