{"id":37899,"date":"2024-11-01T10:01:22","date_gmt":"2024-11-01T10:01:22","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=37899"},"modified":"2024-11-01T11:09:04","modified_gmt":"2024-11-01T11:09:04","slug":"automated-trading-using-deep-learning-and-machine-learning-time-series-forecasting-using-transformer-models-trading-strategy-utilizing-transformer-based-time-series-forecasting-models","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/37899\/","title":{"rendered":"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models."},"content":{"rendered":"

In recent years, the cryptocurrency market has grown rapidly, attracting attention to various investment methods for cryptocurrencies, including Bitcoin. Among these, automated trading systems utilizing deep learning and machine learning technologies have gained significant popularity. This article will specifically discuss how to use the transformer<\/strong> model to predict Bitcoin time series data and develop trading strategies based on it.<\/p>\n

1. Basic Concepts of Deep Learning and Machine Learning<\/h2>\n

Deep learning and machine learning are fields of artificial intelligence that involve algorithms that learn patterns from data to perform predictions or classifications. Machine learning primarily includes techniques that train models based on given data to predict outcomes, while deep learning has the ability to solve more complex and nonlinear problems using artificial neural networks.<\/p>\n

2. Importance of Time Series Prediction<\/h2>\n

The prices of cryptocurrencies like Bitcoin include complex data that changes over time. This data is time series data, which plays a crucial role in predicting the future from past data. To make trading decisions in an unstable market, an efficient prediction model is necessary.<\/p>\n

3. Overview of the Transformer Model<\/h2>\n

The transformer model was first introduced in the field of natural language processing (NLP) and has the advantage of being able to process the entire input sequence simultaneously. This makes it suitable for predicting future values using past time series data. The main components of a transformer are the attention<\/strong> mechanism and the multi-layer encoder-decoder structure<\/strong>.<\/p>\n

3.1 Attention Mechanism<\/h3>\n

The attention mechanism allows each part of the input data to calculate how it relates to one another. By using this technique, one can dynamically assess how much each input value influences other input values.<\/p>\n

3.2 Encoder-Decoder Structure<\/h3>\n

The encoder receives the input data and compresses its inherent meaning to pass it to the next stage. The decoder generates prediction values based on this inherent meaning. This structure is useful even in complex time series predictions.<\/p>\n

4. Preparing Bitcoin Time Series Data<\/h2>\n

To train the model, it is necessary to collect Bitcoin’s time series data. Here, we will introduce the data preprocessing process using the pandas<\/code> library in Python.<\/p>\n

import pandas as pd\nimport numpy as np\n\n# Load data\ndata = pd.read_csv('bitcoin_price.csv')  # Path to the CSV file containing Bitcoin price data\n\n# Convert date to datetime format\ndata['Date'] = pd.to_datetime(data['Date'])\n\n# Select necessary columns\ndata = data[['Date', 'Close']]\n\n# Set index to date\ndata.set_index('Date', inplace=True)\n\n# Handle missing values\ndata = data.fillna(method='ffill')\n\n# Check data\nprint(data.head())<\/code><\/pre>\n
5. Building a Transformer Time Series Prediction Model<\/h2>\n
Now we will build a transformer model using the prepared Bitcoin price data. We will use the TensorFlow<\/strong> and Keras<\/strong> libraries for this purpose.<\/p>\n
5.1 Defining the Transformer Model<\/h3>\n
import tensorflow as tf\nfrom tensorflow import keras\n\ndef create_transformer_model(input_shape, num_heads, ff_dim):\n    inputs = keras.Input(shape=input_shape)\n    attention = keras.layers.MultiHeadAttention(num_heads=num_heads, key_dim=input_shape[-1])(inputs, inputs)\n    x = keras.layers.Add()([inputs, attention])  # Skip connection\n    x = keras.layers.LayerNormalization()(x)\n    x = keras.layers.Dense(ff_dim, activation='relu')(x)  # Feed Forward Network\n    x = keras.layers.Dense(input_shape[-1])(x)\n    x = keras.layers.Add()([inputs, x])  # Skip connection\n    x = keras.layers.LayerNormalization()(x)\n    \n    # Output layer\n    outputs = keras.layers.Dense(1)(x)\n    \n    model = keras.Model(inputs=inputs, outputs=outputs)\n    return model\n\n# Create model\nmodel = create_transformer_model(input_shape=(30, 1), num_heads=4, ff_dim=32)\nmodel.compile(optimizer='adam', loss='mean_squared_error')\n\n# Model summary\nmodel.summary()<\/code><\/pre>\n
5.2 Data Preprocessing and Model Training<\/h3>\n
To train the transformer model, the data needs to be split into sequences of a fixed length.<\/p>\n
def create_sequences(data, seq_length):\n    sequences = []\n    labels = []\n    for i in range(len(data) - seq_length):\n        sequences.append(data[i:i+seq_length])\n        labels.append(data[i+seq_length])\n    return np.array(sequences), np.array(labels)\n\n# Set time series length\nSEQ_LENGTH = 30\n\n# Generate sequences\nsequences, labels = create_sequences(data['Close'].values, SEQ_LENGTH)\n\n# Split into training and validation sets\nsplit_idx = int(len(sequences) * 0.8)\nX_train, X_val = sequences[:split_idx], sequences[split_idx:]\ny_train, y_val = labels[:split_idx], labels[split_idx:]\n\n# Train model\nmodel.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=50, batch_size=32)<\/code><\/pre>\n
6. Building a Trading Strategy<\/h2>\n
Once the model is trained, a realistic trading strategy needs to be established. A basic trading strategy can be based on the following fundamental rules.<\/p>\n
6.1 Generating Buy\/Sell Signals<\/h3>\n
def generate_signals(predictions, threshold=0.01):\n    signals = []\n    for i in range(1, len(predictions)):\n        if predictions[i] > predictions[i - 1] * (1 + threshold):\n            signals.append(1)  # Buy\n        elif predictions[i] < predictions[i - 1] * (1 - threshold):\n            signals.append(-1)  # Sell\n        else:\n            signals.append(0)  # Hold\n    return signals\n\n# Generate predictions\npredictions = model.predict(X_val)\nsignals = generate_signals(predictions.flatten())\n\n# Check signals\nprint(signals[-10:])<\/code><\/pre>\n
7. Evaluating Results<\/h2>\n
Various methods can be used to evaluate the model's performance. For example, accuracy<\/strong>, precision<\/strong>, and recall<\/strong> can be calculated to measure the predictive power of the model. Additionally, the effectiveness of the strategy can be verified by evaluating the returns through actual trading.<\/p>\n
7.1 Calculating Performance Metrics<\/h3>\n
def calculate_performance(signals, actual_prices):\n    portfolio = 10000  # Initial investment amount\n    for i in range(len(signals)):\n        if signals[i] == 1:  # Buy\n            portfolio *= (actual_prices[i+1] \/ actual_prices[i])\n        elif signals[i] == -1:  # Sell\n            portfolio *= (actual_prices[i] \/ actual_prices[i+1])\n    return portfolio\n\n# Calculate performance\nfinal_portfolio_value = calculate_performance(signals, data['Close'].values[-len(signals):])\nprint(f'Final portfolio value: {final_portfolio_value}') \/\/<\/code><\/pre>\n
8. Conclusion<\/h2>\n
An automated trading system for Bitcoin utilizing deep learning and machine learning can process complex time series data to perform predictions. In particular, the transformer model is a very effective tool for predicting future prices based on past data. However, due to the nature of the market, no model can guarantee perfect predictions, and risks must always be taken into account. Therefore, when using such models, it is crucial to formulate a comprehensive strategy alongside various risk management techniques.<\/p>\n
The automated trading system using the transformer model described in this article is expected to continue to evolve. It is important to explore various strategies through data collection and processing, model training, and evaluation in order to build your own investment style.<\/p>\n","protected":false},"excerpt":{"rendered":"
In recent years, the cryptocurrency market has grown rapidly, attracting attention to various investment methods for cryptocurrencies, including Bitcoin. Among these, automated trading systems utilizing deep learning and machine learning technologies have gained significant popularity. This article will specifically discuss how to use the transformer model to predict Bitcoin time series data and develop trading … \ub354 \ubcf4\uae30 “Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models.”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[121],"tags":[],"class_list":["post-37899","post","type-post","status-publish","format-standard","hentry","category-deep-learning-automated-trading"],"yoast_head":"\nAutomated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models. - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/atmokpo.com\/w\/37899\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models. - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"In recent years, the cryptocurrency market has grown rapidly, attracting attention to various investment methods for cryptocurrencies, including Bitcoin. Among these, automated trading systems utilizing deep learning and machine learning technologies have gained significant popularity. This article will specifically discuss how to use the transformer model to predict Bitcoin time series data and develop trading … \ub354 \ubcf4\uae30 "Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models."\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/37899\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-01T10:01:22+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-01T11:09:04+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"5\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/37899\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/37899\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models.\",\"datePublished\":\"2024-11-01T10:01:22+00:00\",\"dateModified\":\"2024-11-01T11:09:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/37899\/\"},\"wordCount\":625,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"Deep learning Automated trading\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/37899\/\",\"url\":\"https:\/\/atmokpo.com\/w\/37899\/\",\"name\":\"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models. - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-01T10:01:22+00:00\",\"dateModified\":\"2024-11-01T11:09:04+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/37899\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/37899\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/37899\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models.\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models. - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/atmokpo.com\/w\/37899\/","og_locale":"ko_KR","og_type":"article","og_title":"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models. - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"In recent years, the cryptocurrency market has grown rapidly, attracting attention to various investment methods for cryptocurrencies, including Bitcoin. Among these, automated trading systems utilizing deep learning and machine learning technologies have gained significant popularity. This article will specifically discuss how to use the transformer model to predict Bitcoin time series data and develop trading … \ub354 \ubcf4\uae30 \"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models.\"","og_url":"https:\/\/atmokpo.com\/w\/37899\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-01T10:01:22+00:00","article_modified_time":"2024-11-01T11:09:04+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"5\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/37899\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/37899\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models.","datePublished":"2024-11-01T10:01:22+00:00","dateModified":"2024-11-01T11:09:04+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/37899\/"},"wordCount":625,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["Deep learning Automated trading"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/37899\/","url":"https:\/\/atmokpo.com\/w\/37899\/","name":"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models. - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-01T10:01:22+00:00","dateModified":"2024-11-01T11:09:04+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/37899\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/37899\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/37899\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"Automated trading using deep learning and machine learning, time series forecasting using transformer models. Trading strategy utilizing transformer-based time series forecasting models."}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/37899","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=37899"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/37899\/revisions"}],"predecessor-version":[{"id":37900,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/37899\/revisions\/37900"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=37899"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=37899"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=37899"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}