Cheng Siong Chin This workflow corresponds to n8n.io template #10624 — we link there as the canonical source.
This workflow follows the Agent → Emailsend recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "bNDL8d7av4vO7Uym",
"name": "Singapore COE Price Scraping & GLM-4.5 Prediction with Purchase Timing Recommendation",
"tags": [],
"nodes": [
{
"id": "f0630256-92c3-4f3d-9bd6-4a93ced66909",
"name": "Schedule Trigger - Bi-Weekly COE Scraping",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
64,
384
],
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 20 * * 3"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "0e1e24c9-35cc-45f1-bc03-51bef5e4a48b",
"name": "Scrape COE Data from OneMotoring",
"type": "n8n-nodes-base.httpRequest",
"position": [
320,
384
],
"parameters": {
"url": "https://onemotoring.lta.gov.sg/content/onemotoring/home/buying/upfront-vehicle-costs/certificate-of-entitlement--coe-.html",
"options": {
"timeout": 30000
}
},
"typeVersion": 4.2
},
{
"id": "75af2713-c37a-40b6-9eb8-a321d1e52a2a",
"name": "Extract COE Price Data",
"type": "n8n-nodes-base.code",
"position": [
512,
384
],
"parameters": {
"jsCode": "const html = $input.item.json.data;\nconst cheerio = require('cheerio');\nconst $ = cheerio.load(html);\n\nconst categories = ['Category A', 'Category B', 'Category C', 'Category D', 'Category E'];\nconst coeData = [];\nconst biddingDate = new Date().toISOString().split('T')[0];\n\n$('table tbody tr').each((index, row) => {\n const cells = $(row).find('td');\n if (cells.length >= 4) {\n const category = $(cells[0]).text().trim();\n const quotaPremium = parseFloat($(cells[1]).text().replace(/[^0-9.]/g, ''));\n const quotaAvailable = parseInt($(cells[2]).text().replace(/[^0-9]/g, ''));\n const bidsReceived = parseInt($(cells[3]).text().replace(/[^0-9]/g, ''));\n \n if (categories.some(cat => category.includes(cat))) {\n coeData.push({\n biddingDate,\n category,\n quotaPremium,\n quotaAvailable,\n bidsReceived,\n timestamp: new Date().toISOString()\n });\n }\n }\n});\n\nreturn coeData.map(item => ({ json: item }));"
},
"typeVersion": 2
},
{
"id": "4c4d36f4-439a-402f-95c1-12450ab8e53a",
"name": "Store in Google Sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
704,
384
],
"parameters": {
"columns": {
"value": {
"category": "={{ $json.category }}",
"timestamp": "={{ $json.timestamp }}",
"biddingDate": "={{ $json.biddingDate }}",
"bidsReceived": "={{ $json.bidsReceived }}",
"quotaPremium": "={{ $json.quotaPremium }}",
"quotaAvailable": "={{ $json.quotaAvailable }}"
},
"mappingMode": "defineBelow"
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "name",
"value": "COE Historical Data"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "{{ $json.spreadsheetId }}"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.5
},
{
"id": "9e035479-59b9-48a9-951e-b9ced757a9c2",
"name": "Retrieve Historical COE Data",
"type": "n8n-nodes-base.googleSheets",
"position": [
896,
384
],
"parameters": {
"options": {},
"sheetName": {
"__rl": true,
"mode": "name",
"value": "COE Historical Data"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.spreadsheetId }}"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.5
},
{
"id": "5437ef61-879f-4b99-9740-c2940af16055",
"name": "Calculate Technical Indicators",
"type": "n8n-nodes-base.code",
"position": [
1072,
384
],
"parameters": {
"jsCode": "const items = $input.all();\nconst categories = ['Category A', 'Category B', 'Category C', 'Category D', 'Category E'];\n\nconst processedData = {};\n\ncategories.forEach(category => {\n const categoryData = items.filter(item => \n item.json.category && item.json.category.includes(category)\n ).sort((a, b) => new Date(a.json.biddingDate) - new Date(b.json.biddingDate));\n \n if (categoryData.length < 4) {\n processedData[category] = { error: 'Insufficient data' };\n return;\n }\n \n const prices = categoryData.map(item => item.json.quotaPremium);\n const latestPrice = prices[prices.length - 1];\n \n const ma4 = prices.slice(-4).reduce((a, b) => a + b, 0) / 4;\n const ma12 = prices.length >= 12 ? prices.slice(-12).reduce((a, b) => a + b, 0) / 12 : ma4;\n const ma26 = prices.length >= 26 ? prices.slice(-26).reduce((a, b) => a + b, 0) / 26 : ma12;\n \n const rateOfChange = ((latestPrice - prices[prices.length - 5]) / prices[prices.length - 5]) * 100;\n \n const variance = prices.slice(-12).reduce((sum, price) => sum + Math.pow(price - ma12, 2), 0) / Math.min(12, prices.length);\n const volatility = Math.sqrt(variance);\n \n const now = new Date();\n const month = now.getMonth() + 1;\n const quarter = Math.ceil(month / 3);\n const isCNYPeriod = month === 1 || month === 2;\n const isYearEnd = month === 11 || month === 12;\n \n processedData[category] = {\n latestPrice,\n ma4,\n ma12,\n ma26,\n rateOfChange,\n volatility,\n month,\n quarter,\n isCNYPeriod,\n isYearEnd,\n historicalPrices: prices.slice(-26),\n dataPoints: categoryData.length\n };\n});\n\nreturn [{ json: processedData }];"
},
"typeVersion": 2
},
{
"id": "a4ac811d-1308-4c49-bb12-353f82ce7a61",
"name": "Prepare AI Prediction Prompt",
"type": "n8n-nodes-base.set",
"position": [
1264,
384
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "1",
"name": "predictionPrompt",
"type": "string",
"value": "=You are a Singapore COE market analysis expert. Analyze the following COE data and provide detailed price predictions:\n\n{{ Object.keys($json).map(category => {\n const data = $json[category];\n return `${category}:\n- Latest Price: $${data.latestPrice}\n- 4-week MA: $${data.ma4?.toFixed(0)}\n- 12-week MA: $${data.ma12?.toFixed(0)}\n- 26-week MA: $${data.ma26?.toFixed(0)}\n- Rate of Change: ${data.rateOfChange?.toFixed(2)}%\n- Volatility: $${data.volatility?.toFixed(0)}\n- Current Period: Q${data.quarter}, Month ${data.month}\n- CNY Period: ${data.isCNYPeriod}\n- Year-End Period: ${data.isYearEnd}\n- Historical Prices (last 26 weeks): ${data.historicalPrices?.join(', ')}`;\n}).join('\\n\\n') }}\n\nProvide:\n1. Price predictions for next 6 bidding rounds (3 months) for each category\n2. Confidence levels (High/Medium/Low) for each prediction\n3. Market trend analysis (uptrend/downtrend/consolidation)\n4. Seasonal factors impact\n5. Risk assessment\n\nFormat as JSON:\n{\n \"predictions\": {\n \"Category A\": [{\"round\": 1, \"predictedPrice\": 95000, \"confidence\": \"High\", \"lower\": 92000, \"upper\": 98000}, ...],\n ...\n },\n \"trends\": {\"Category A\": \"uptrend\", ...},\n \"seasonalImpact\": \"High impact expected due to...\",\n \"riskLevel\": \"Medium\"\n}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "5733ab85-b2bb-4d63-a207-3b8d5cc16c36",
"name": "AI Agent - COE Analysis",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1424,
384
],
"parameters": {
"text": "={{ $json.predictionPrompt }}",
"options": {}
},
"typeVersion": 1.7
},
{
"id": "bd9f5443-2781-4f8b-9802-cdadf23f6e2c",
"name": "Generate Buy Recommendations",
"type": "n8n-nodes-base.code",
"position": [
1744,
384
],
"parameters": {
"jsCode": "const technicalData = $('Calculate Technical Indicators').first().json;\nconst aiPrediction = $input.first().json;\n\nconst categories = Object.keys(technicalData);\nconst recommendations = {};\n\ncategories.forEach(category => {\n const tech = technicalData[category];\n if (tech.error) {\n recommendations[category] = { action: 'Insufficient Data', reasoning: tech.error };\n return;\n }\n \n let score = 50;\n let reasoning = [];\n \n if (tech.latestPrice < tech.ma12) {\n score += 15;\n reasoning.push('Price below 12-week average (bullish signal)');\n } else if (tech.latestPrice > tech.ma12 * 1.1) {\n score -= 15;\n reasoning.push('Price significantly above moving average (overheated)');\n }\n \n if (tech.rateOfChange < -5) {\n score += 20;\n reasoning.push(`Strong downward momentum (${tech.rateOfChange.toFixed(1)}%)`);\n } else if (tech.rateOfChange > 10) {\n score -= 20;\n reasoning.push(`Strong upward momentum (${tech.rateOfChange.toFixed(1)}%) - avoid buying`);\n }\n \n if (tech.isCNYPeriod) {\n score -= 10;\n reasoning.push('CNY period typically sees higher prices');\n }\n \n if (tech.isYearEnd) {\n score -= 5;\n reasoning.push('Year-end period - slightly elevated demand');\n }\n \n if (tech.volatility > tech.ma12 * 0.15) {\n score -= 10;\n reasoning.push('High volatility - uncertain market conditions');\n }\n \n let action, timingAdvice, potentialSavings;\n if (score >= 70) {\n action = 'BUY NOW';\n timingAdvice = 'Strong buying opportunity. Market conditions favorable.';\n potentialSavings = 0;\n } else if (score >= 50) {\n action = 'MONITOR CLOSELY';\n timingAdvice = 'Market at neutral position. Consider waiting 2-4 weeks.';\n potentialSavings = Math.round(tech.latestPrice * 0.03);\n } else {\n action = 'WAIT';\n const weeksToWait = score < 30 ? 8 : 4;\n timingAdvice = `Wait ${weeksToWait} weeks. Market showing unfavorable conditions.`;\n potentialSavings = Math.round(tech.latestPrice * 0.08);\n }\n \n recommendations[category] = {\n action,\n score,\n currentPrice: tech.latestPrice,\n timingAdvice,\n potentialSavings,\n reasoning: reasoning.join('; '),\n trend: tech.rateOfChange > 5 ? 'Uptrend' : tech.rateOfChange < -5 ? 'Downtrend' : 'Consolidation',\n volatilityLevel: tech.volatility > tech.ma12 * 0.15 ? 'High' : tech.volatility > tech.ma12 * 0.08 ? 'Medium' : 'Low'\n };\n});\n\nconst bestCategory = Object.entries(recommendations)\n .filter(([_, rec]) => !rec.reasoning.includes('Insufficient'))\n .sort((a, b) => b[1].score - a[1].score)[0];\n\nreturn [{\n json: {\n recommendations,\n bestCategory: bestCategory ? bestCategory[0] : 'None',\n bestCategoryScore: bestCategory ? bestCategory[1].score : 0,\n analysisDate: new Date().toISOString(),\n marketOverview: {\n averageVolatility: Object.values(recommendations)\n .filter(r => r.volatilityLevel)\n .reduce((sum, r) => sum + (r.volatilityLevel === 'High' ? 3 : r.volatilityLevel === 'Medium' ? 2 : 1), 0) / categories.length,\n dominantTrend: Object.values(recommendations)\n .filter(r => r.trend)\n .reduce((acc, r) => {\n acc[r.trend] = (acc[r.trend] || 0) + 1;\n return acc;\n }, {})\n }\n }\n}];"
},
"typeVersion": 2
},
{
"id": "3b384a83-df2f-4845-9017-ffcb2b377dc6",
"name": "Format HTML Report",
"type": "n8n-nodes-base.code",
"position": [
2000,
192
],
"parameters": {
"jsCode": "const recommendations = $input.first().json.recommendations;\nconst bestCategory = $input.first().json.bestCategory;\nconst analysisDate = new Date($input.first().json.analysisDate).toLocaleDateString('en-SG');\n\nlet htmlReport = `\n<!DOCTYPE html>\n<html>\n<head>\n <style>\n body { font-family: Arial, sans-serif; margin: 20px; background: #f5f5f5; }\n .container { max-width: 1200px; margin: 0 auto; background: white; padding: 30px; border-radius: 10px; box-shadow: 0 2px 10px rgba(0,0,0,0.1); }\n h1 { color: #d32f2f; border-bottom: 3px solid #d32f2f; padding-bottom: 10px; }\n h2 { color: #1976d2; margin-top: 30px; }\n .category-card { background: #f9f9f9; padding: 20px; margin: 15px 0; border-radius: 8px; border-left: 5px solid #1976d2; }\n .buy-now { border-left-color: #4caf50; background: #e8f5e9; }\n .wait { border-left-color: #f44336; background: #ffebee; }\n .monitor { border-left-color: #ff9800; background: #fff3e0; }\n .action { font-size: 24px; font-weight: bold; margin-bottom: 10px; }\n .action.buy { color: #4caf50; }\n .action.wait { color: #f44336; }\n .action.monitor { color: #ff9800; }\n .price { font-size: 32px; font-weight: bold; color: #333; }\n .metric { display: inline-block; margin: 10px 20px 10px 0; }\n .metric-label { font-weight: bold; color: #666; }\n .savings { background: #4caf50; color: white; padding: 10px 15px; border-radius: 5px; display: inline-block; margin-top: 10px; }\n .reasoning { background: white; padding: 15px; border-radius: 5px; margin-top: 10px; font-size: 14px; color: #555; }\n .best-pick { background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); color: white; padding: 20px; border-radius: 10px; margin: 20px 0; }\n .footer { margin-top: 40px; padding-top: 20px; border-top: 2px solid #eee; color: #999; font-size: 12px; text-align: center; }\n </style>\n</head>\n<body>\n <div class=\"container\">\n <h1>\ud83d\ude97 Singapore COE Price Analysis & Recommendations</h1>\n <p><strong>Analysis Date:</strong> ${analysisDate}</p>\n \n <div class=\"best-pick\">\n <h2 style=\"color: white; margin-top: 0;\">\u2b50 Best Category to Consider</h2>\n <p style=\"font-size: 20px; margin: 10px 0;\">${bestCategory}</p>\n <p>Highest recommendation score based on current market conditions</p>\n </div>\n`;\n\nObject.entries(recommendations).forEach(([category, rec]) => {\n if (rec.reasoning && rec.reasoning.includes('Insufficient')) {\n htmlReport += `\n <div class=\"category-card\">\n <h2>${category}</h2>\n <p>${rec.reasoning}</p>\n </div>\n `;\n return;\n }\n \n const cardClass = rec.action === 'BUY NOW' ? 'buy-now' : rec.action === 'WAIT' ? 'wait' : 'monitor';\n const actionClass = rec.action === 'BUY NOW' ? 'buy' : rec.action === 'WAIT' ? 'wait' : 'monitor';\n \n htmlReport += `\n <div class=\"category-card ${cardClass}\">\n <h2>${category}</h2>\n <div class=\"action ${actionClass}\">${rec.action === 'BUY NOW' ? '\u2705' : rec.action === 'WAIT' ? '\u23f8\ufe0f' : '\ud83d\udc40'} ${rec.action}</div>\n <div class=\"price\">$${rec.currentPrice.toLocaleString('en-SG')}</div>\n <div class=\"metric\">\n <span class=\"metric-label\">Score:</span> ${rec.score}/100\n </div>\n <div class=\"metric\">\n <span class=\"metric-label\">Trend:</span> ${rec.trend}\n </div>\n <div class=\"metric\">\n <span class=\"metric-label\">Volatility:</span> ${rec.volatilityLevel}\n </div>\n <p><strong>Timing Advice:</strong> ${rec.timingAdvice}</p>\n ${rec.potentialSavings > 0 ? `<div class=\"savings\">\ud83d\udcb0 Potential Savings: $${rec.potentialSavings.toLocaleString('en-SG')}</div>` : ''}\n <div class=\"reasoning\">\n <strong>Analysis:</strong><br>\n ${rec.reasoning}\n </div>\n </div>\n `;\n});\n\nhtmlReport += `\n <div class=\"footer\">\n <p>This analysis is based on historical COE data and market trends. Actual prices may vary.</p>\n <p>Data source: LTA OneMotoring Portal | Generated by n8n Automation</p>\n </div>\n </div>\n</body>\n</html>\n`;\n\nreturn [{ json: { htmlReport, subject: `COE Analysis Report - ${analysisDate}` } }];"
},
"typeVersion": 2
},
{
"id": "509457b5-5626-4869-9db2-da1eff8a0e20",
"name": "Send Email Report",
"type": "n8n-nodes-base.emailSend",
"position": [
2224,
192
],
"parameters": {
"options": {},
"subject": "={{ $json.subject }}",
"toEmail": "user@example.com",
"fromEmail": "user@example.com"
},
"typeVersion": 2.1
},
{
"id": "8f0f99a2-3cb3-4bfd-acda-179434d27b21",
"name": "Check for Buy Opportunities",
"type": "n8n-nodes-base.if",
"position": [
2000,
384
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "1",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.recommendations['Category A'].action }}",
"rightValue": "BUY NOW"
},
{
"id": "2",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.recommendations['Category B'].action }}",
"rightValue": "BUY NOW"
}
]
}
},
"typeVersion": 2.1
},
{
"id": "dd4f819f-2115-41bb-a472-6149662d2e20",
"name": "Send Telegram Alert",
"type": "n8n-nodes-base.telegram",
"position": [
2224,
368
],
"parameters": {
"text": "=\ud83d\udea8 *COE BUY ALERT* \ud83d\udea8\n\nOptimal buying opportunity detected!\n\n{{ Object.entries($json.recommendations)\n .filter(([_, rec]) => rec.action === 'BUY NOW')\n .map(([cat, rec]) => `*${cat}*: $${rec.currentPrice.toLocaleString('en-SG')}\\nScore: ${rec.score}/100\\n${rec.timingAdvice}`)\n .join('\\n\\n') }}\n\nView full report in your email.",
"chatId": "{{ $('Schedule Trigger - Bi-Weekly COE Scraping').item.json.telegramChatId }}",
"additionalFields": {
"parse_mode": "Markdown"
}
},
"typeVersion": 1.2
},
{
"id": "b08a514c-b77d-46d2-a928-70efd0ef643a",
"name": "Generate Dashboard Summary",
"type": "n8n-nodes-base.set",
"position": [
2000,
576
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "1",
"name": "dashboardSummary",
"type": "string",
"value": "=## Singapore COE Dashboard - {{ new Date().toLocaleDateString('en-SG') }}\n\n### Current Prices\n{{ Object.entries($('Generate Buy Recommendations').first().json.recommendations)\n .map(([cat, rec]) => `**${cat}**: $${rec.currentPrice?.toLocaleString('en-SG') || 'N/A'}`)\n .join('\\n') }}\n\n### Top Recommendation\n**{{ $('Generate Buy Recommendations').first().json.bestCategory }}** (Score: {{ $('Generate Buy Recommendations').first().json.bestCategoryScore }}/100)\n\n### Market Overview\n- Dominant Trend: {{ Object.entries($('Generate Buy Recommendations').first().json.marketOverview.dominantTrend).sort((a,b) => b[1] - a[1])[0][0] }}\n- Average Volatility: {{ $('Generate Buy Recommendations').first().json.marketOverview.averageVolatility > 2.5 ? 'High' : $('Generate Buy Recommendations').first().json.marketOverview.averageVolatility > 1.5 ? 'Medium' : 'Low' }}\n\n### Action Items\n{{ Object.entries($('Generate Buy Recommendations').first().json.recommendations)\n .map(([cat, rec]) => `- **${cat}**: ${rec.action} - ${rec.timingAdvice}`)\n .join('\\n') }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "2ce78f73-1b51-43b9-94cf-e6b7ce7544df",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
-64
],
"parameters": {
"width": 992,
"height": 384,
"content": "## Introduction\nAutomates Singapore COE price tracking, predicts trends using AI, and recommends optimal car purchase timing. Scrapes LTA data biweekly, analyzes historical trends, forecasts next 6 bidding rounds, and sends alerts when buying windows appear\u2014saving time and identifying cost-saving opportunities.\n\n## How it Works\nBiweekly trigger scrapes LTA COE data \u2192 processes historical trends \u2192 AI predicts 6-month prices \u2192 compares current vs forecast \u2192 generates buy/wait recommendations \u2192 alerts sent via Gmail or Telegram.\n\n## Setup Steps\n1. Add NVIDIA/OpenAI API credentials in n8n\n2. Connect Google Sheets for data storage\n3. Authenticate Gmail/Telegram for notifications\n4. Schedule trigger for Wednesdays 8PM SGT\n5. Configure alert thresholds in conditional nodes\n\n"
},
"typeVersion": 1
},
{
"id": "ec982981-33f8-4e23-97bc-8fddeb3db95a",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1056,
-64
],
"parameters": {
"color": 4,
"width": 512,
"height": 224,
"content": "## Prerequisites\nNVIDIA/OpenAI API key, Google account (Sheets), Gmail/Telegram for notifications, basic COE category knowledge\n\n## Use Cases\nFirst-time buyers monitoring price dips, fleet managers timing bulk purchases\n"
},
"typeVersion": 1
},
{
"id": "356985f8-b8b9-4166-9267-06607e03e479",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1632,
-64
],
"parameters": {
"color": 5,
"width": 544,
"height": 224,
"content": "## Customization\nAdd economic indicators, integrate car loan calculators, track parallel imported car prices\n\n## Benefits\nSaves hours of manual monitoring, captures 10\u201315% price dips, provides data-driven purchase timing (potential $5K\u2013$15K savings)"
},
"typeVersion": 1
},
{
"id": "3ef5c1ec-d77f-450b-b446-ba0f20847718",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
560
],
"parameters": {
"color": 6,
"width": 752,
"height": 96,
"content": "## Workflow\nSchedule Trigger \u2192 HTTP Request (Scrape LTA) \u2192 Data Processing \u2192 Google Sheets (Store) \u2192 AI Prediction \u2192 Analysis Engine \u2192 Conditional Logic \u2192 Gmail/Telegram Notification\n\n"
},
"typeVersion": 1
},
{
"id": "59139375-d79a-4bf8-a073-de197b6b5456",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
1424,
560
],
"parameters": {
"model": "z-ai/glm-4.5",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "d67e15bf-2829-4e99-adb3-43f841d34020",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
784,
560
],
"parameters": {
"color": 3,
"width": 576,
"height": 192,
"content": "## Workflow Steps\n1. Scraping: Extract COE prices from OneMotoring\n2. Processing: Calculate moving averages, volatility, seasonal trends\n3. Storage: Save to Google Sheets with timestamps\n4. Prediction: AI forecasts next 6 bidding rounds\n5. Analysis: Compare current vs predicted prices, generate recommendation\n6. Notification: Alerts via email/Telegram"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "793fae3d-cde8-4016-ad16-e27224d55ff7",
"connections": {
"Format HTML Report": {
"main": [
[
{
"node": "Send Email Report",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent - COE Analysis",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Extract COE Price Data": {
"main": [
[
{
"node": "Store in Google Sheets",
"type": "main",
"index": 0
}
]
]
},
"Store in Google Sheets": {
"main": [
[
{
"node": "Retrieve Historical COE Data",
"type": "main",
"index": 0
}
]
]
},
"AI Agent - COE Analysis": {
"main": [
[
{
"node": "Generate Buy Recommendations",
"type": "main",
"index": 0
}
]
]
},
"Check for Buy Opportunities": {
"main": [
[
{
"node": "Send Telegram Alert",
"type": "main",
"index": 0
}
]
]
},
"Generate Buy Recommendations": {
"main": [
[
{
"node": "Format HTML Report",
"type": "main",
"index": 0
},
{
"node": "Check for Buy Opportunities",
"type": "main",
"index": 0
},
{
"node": "Generate Dashboard Summary",
"type": "main",
"index": 0
}
]
]
},
"Prepare AI Prediction Prompt": {
"main": [
[
{
"node": "AI Agent - COE Analysis",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Historical COE Data": {
"main": [
[
{
"node": "Calculate Technical Indicators",
"type": "main",
"index": 0
}
]
]
},
"Calculate Technical Indicators": {
"main": [
[
{
"node": "Prepare AI Prediction Prompt",
"type": "main",
"index": 0
}
]
]
},
"Scrape COE Data from OneMotoring": {
"main": [
[
{
"node": "Extract COE Price Data",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger - Bi-Weekly COE Scraping": {
"main": [
[
{
"node": "Scrape COE Data from OneMotoring",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleSheetsOAuth2ApiopenRouterApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Automates Singapore COE price tracking, predicts trends using AI, and recommends optimal car purchase timing. Scrapes LTA data biweekly, analyzes historical trends, forecasts next 6 bidding rounds, and sends alerts when buying windows appear—saving time and identifying…
Source: https://n8n.io/workflows/10624/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This cutting-edge n8n workflow is a comprehensive automation solution designed to streamline various Instagram operations. It combines an intelligent AI chatbot for direct message management, automate
Agent, OpenRouter Chat, Output Parser Structured +4
This workflow is for beauty salons who want consistent, high‑quality social media content without writing every post manually. It also suits agencies and automation builders who manage multiple beauty
Telegram, Google Sheets Trigger, Agent +26
This n8n workflow turns a script and character/setting description from Google Sheets into a complete stitched UGC-style video ad, fully automated from intake to final delivery.
Google Sheets, HTTP Request, OpenRouter Chat +7
This workflow automates the creation, rendering, approval, and posting of TikTok-style POV (Point of View) videos to Instagram, with cross-posting to Facebook and YouTube. It eliminates manual video p
OpenAI Chat, Output Parser Item List, HTTP Request +10
This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents.
Tool Http Request, Agent, HTTP Request +27