develop indicator for trading view (BBMA and fibo musang) with alert
Budget: $250 – $750 USD
Your project specification is already highly detailed. Below is a refined and more professionally structured version with the new dual-layer system architecture added properly:
Training Mode
Prediction Mode
This structure is cleaner, more scalable, and closer to enterprise AI system design.
APP DEVELOPMENT SPECIFICATION
APPLICATION NAME
Amir B From Malaysia
FCPO Shariah Compliant Market Only
============================================================
PLATFORM & DEPLOYMENT
Operating System
Windows Platform
Application Interface
Command Prompt Interface (CMD)
Deployment Format
Standalone Windows .EXE Application
Execution Environment
Fully Offline Execution
Lightweight System Architecture
High-Speed Processing Engine
Optimized CPU & RAM Utilization
Stable for Continuous Daily FCPO Analysis
Fast Startup & Low-Latency Prediction Engine
Security & Licensing
Encrypted License Key Authentication System
License Options
Lifetime License
3-Year Expiry License
License Requirement
Application cannot execute without valid license authentication
============================================================
SYSTEM OBJECTIVE
The application must analyze historical FCPO OHLC Excel datasets and generate:
Next-Day Market Direction Prediction
Same-Day Market Direction Prediction using today Open price before market close
The AI framework must integrate:
Machine Learning
Statistical Modeling
Volatility Modeling
Deep Learning
Market Structure Analysis
Ensemble Optimization
Adaptive Market Learning
============================================================
MARKET PREDICTION LOGIC
BUY
Expected Close Price > Open Price
SELL
Expected Close Price < Open Price
Optional: NO TRADE
Triggered when:
prediction confidence is weak
market structure is unstable
AI consensus is conflicting
volatility condition is abnormal
============================================================
DATA SOURCE & EXCEL INTEGRATION
The application must support manual Excel integration.
Supported Excel Columns
Date
Open
High
Low
Close
User Functions
Paste Excel file directory manually
Update Excel data anytime
Save latest candle data manually
Instantly rerun analysis
Automatically retrain after new data entry
Example Path
D:\FCPO\data.xlsx
============================================================
TRAINING MODE ARCHITECTURE
The application must separate:
AI Training Mode
Prediction Mode
This allows flexible combinations between:
full retraining
saved model execution
next-day prediction
same-day prediction
============================================================
TRAINING MODES
1. RUN USING LAST MACHINE LEARNING
Purpose: Use the latest saved trained AI models for faster execution.
Functions:
Load latest trained model state
Load latest optimized ensemble weighting
Perform incremental retraining on newest candle data only
Fast operational analysis mode
Optimized for daily usage
Advantages:
Faster execution
Lower CPU usage
Faster prediction generation
Suitable for continuous daily operation
============================================================
2. RE-RUN MACHINE LEARNING FROM FIRST DATA
Purpose: Perform complete AI rebuilding from earliest historical dataset.
Functions:
Retrain all models from beginning
Rebuild ensemble structure
Recalculate feature importance
Perform deep optimization cycle
Execute full walk-forward backtesting
Recalibrate confidence weighting
Advantages:
Maximum optimization quality
Full AI recalibration
Better long-term adaptation
More stable ensemble rebuilding
============================================================
PREDICTION MODES
1. RUN NEXT-DAY MARKET PREDICTION
Purpose: Predict next FCPO trading day direction using completed OHLC historical candles.
Prediction Output:
BUY
SELL
NO TRADE
Analysis Components:
historical market behavior
volatility structure
momentum continuation
market regime analysis
trend continuation probability
ensemble confidence weighting
============================================================
2. RUN TODAY MARKET PREDICTION
Purpose: Predict whether the current FCPO trading day is likely to close bullish or bearish BEFORE market close.
The prediction must use today Open price together with historical FCPO market behavior and live market structure analysis.
============================================================
SAME-DAY AI INPUT ENGINE
For stronger same-day prediction accuracy, the AI engine must analyze:
Today Open Price
Previous Day OHLC
Previous Volatility Structure
Previous Momentum Structure
Current Market Regime
Historical FCPO Market Behavior
Historical Trend Continuation Patterns
AI Ensemble Probability Distribution
Optional Additional Inputs
Intraday Price Movement
Intraday Volatility Expansion
Early Session Momentum Shift
============================================================
SAME-DAY MARKET PREDICTION LOGIC
BUY
Expected Today Close > Today Open
SELL
Expected Today Close < Today Open
Optional: NO TRADE
Triggered when:
intraday structure becomes unstable
AI confidence weakens
volatility becomes abnormal
ensemble signals conflict
============================================================
LIVE MARKET ANALYSIS ENGINE
The system must dynamically evaluate:
bullish vs bearish pressure
trend continuation probability
volatility expansion probability
market structure transition
historical behavioral similarity
AI ensemble confidence
regime transition probability
momentum persistence strength
Prediction confidence must improve dynamically as more market data becomes available during trading hours.
============================================================
AI & MATHEMATICAL ENGINE
The application must initially test ALL mathematical models during historical optimization and backtesting before determining final ensemble weighting.
CORE AI ENGINE
XGBoost
LightGBM
CatBoost
SVM
VOLATILITY ENGINE
GARCH
EGARCH
Heston Model
Stochastic Volatility Model
MARKET STRUCTURE ENGINE
Structural VAR
VECM
Hidden Markov Model (HMM)
TREND FILTER ENGINE
Kalman Filter
DEEP LEARNING ENGINE
LSTM
GRU
SUPPORTING MODELS
Random Forest
Bayesian Network
ARIMA
SARIMA
Monte Carlo Simulation
FINAL AI ENGINE
Stacking Ensemble Model
============================================================
AI SYSTEM DESIGN REQUIREMENTS
The application must NOT remove any mathematical models before full historical backtesting and optimization are completed.
System Requirements
test all models
test all model combinations
compare historical accuracy
compare prediction stability
compare retraining efficiency
compare overfitting risk
compare market adaptability
compare long-term consistency
compare regime sensitivity
compare confidence calibration
Post-Optimization Logic
After optimization:
weaker models may receive lower weighting
unstable models may be disabled
stronger models may receive higher ensemble priority
Primary Objectives
highest realistic prediction accuracy
stable BUY/SELL prediction
adaptive market learning
smooth retraining workflow
fast analysis execution
sustainable long-term stability
minimal overfitting risk
strong confidence calibration
stable live-market prediction performance
============================================================
SMART AUTO-RETRAINING SYSTEM
The application must automatically retrain whenever new Excel candle data is detected.
When new candle data is added:
System Actions
Detect newly added rows automatically
Update:
market structure
volatility regime
trend direction
AI feature layers
historical sequence learning
ensemble confidence
momentum state
market condition classification
Retrain AI models automatically
Reoptimize:
ensemble weighting
feature importance
model confidence
prediction stability
signal reliability
model prioritization
Generate latest prediction automatically
============================================================
USER WORKFLOW
STEP 1
Open Application
STEP 2
Enter License Key
STEP 3
Paste Excel File Directory
STEP 4
Select Training Mode
RUN USING LAST MACHINE LEARNING
RE-RUN MACHINE LEARNING FROM FIRST DATA
STEP 5
Select Prediction Mode
RUN NEXT-DAY MARKET PREDICTION
RUN TODAY MARKET PREDICTION
STEP 6
Click RUN ANALYSIS
STEP 7
Application automatically:
load Excel dataset
validate market data
update AI learning
retrain models
optimize ensemble
generate prediction
display final market signal
============================================================
SYSTEM ARCHITECTURE
Frontend
Command Prompt Interface
Backend
Python AI Engine
Data Source
Excel OHLC Dataset
AI Framework
Hybrid Machine Learning + Statistical Models
Training System
Smart Automatic Retraining Engine
Prediction Output
BUY / SELL / NO TRADE
Deployment
Standalone Windows .EXE Application
============================================================
FINAL DELIVERY REQUIREMENT
The entire application must be fully completed, including:
AI engine development
smart retraining architecture
optimization workflow
historical backtesting engine
Windows .EXE packaging
encrypted license key system
Excel integration
automatic retraining workflow
prediction logging system
user operation manual
Final User Workflow
Download application
Enter license key
Link Excel dataset
Select training mode
Select prediction mode
Run analysis
============================================================
Training Mode
Prediction Mode
This structure is cleaner, more scalable, and closer to enterprise AI system design.
APP DEVELOPMENT SPECIFICATION
APPLICATION NAME
Amir B From Malaysia
FCPO Shariah Compliant Market Only
============================================================
PLATFORM & DEPLOYMENT
Operating System
Windows Platform
Application Interface
Command Prompt Interface (CMD)
Deployment Format
Standalone Windows .EXE Application
Execution Environment
Fully Offline Execution
Lightweight System Architecture
High-Speed Processing Engine
Optimized CPU & RAM Utilization
Stable for Continuous Daily FCPO Analysis
Fast Startup & Low-Latency Prediction Engine
Security & Licensing
Encrypted License Key Authentication System
License Options
Lifetime License
3-Year Expiry License
License Requirement
Application cannot execute without valid license authentication
============================================================
SYSTEM OBJECTIVE
The application must analyze historical FCPO OHLC Excel datasets and generate:
Next-Day Market Direction Prediction
Same-Day Market Direction Prediction using today Open price before market close
The AI framework must integrate:
Machine Learning
Statistical Modeling
Volatility Modeling
Deep Learning
Market Structure Analysis
Ensemble Optimization
Adaptive Market Learning
============================================================
MARKET PREDICTION LOGIC
BUY
Expected Close Price > Open Price
SELL
Expected Close Price < Open Price
Optional: NO TRADE
Triggered when:
prediction confidence is weak
market structure is unstable
AI consensus is conflicting
volatility condition is abnormal
============================================================
DATA SOURCE & EXCEL INTEGRATION
The application must support manual Excel integration.
Supported Excel Columns
Date
Open
High
Low
Close
User Functions
Paste Excel file directory manually
Update Excel data anytime
Save latest candle data manually
Instantly rerun analysis
Automatically retrain after new data entry
Example Path
D:\FCPO\data.xlsx
============================================================
TRAINING MODE ARCHITECTURE
The application must separate:
AI Training Mode
Prediction Mode
This allows flexible combinations between:
full retraining
saved model execution
next-day prediction
same-day prediction
============================================================
TRAINING MODES
1. RUN USING LAST MACHINE LEARNING
Purpose: Use the latest saved trained AI models for faster execution.
Functions:
Load latest trained model state
Load latest optimized ensemble weighting
Perform incremental retraining on newest candle data only
Fast operational analysis mode
Optimized for daily usage
Advantages:
Faster execution
Lower CPU usage
Faster prediction generation
Suitable for continuous daily operation
============================================================
2. RE-RUN MACHINE LEARNING FROM FIRST DATA
Purpose: Perform complete AI rebuilding from earliest historical dataset.
Functions:
Retrain all models from beginning
Rebuild ensemble structure
Recalculate feature importance
Perform deep optimization cycle
Execute full walk-forward backtesting
Recalibrate confidence weighting
Advantages:
Maximum optimization quality
Full AI recalibration
Better long-term adaptation
More stable ensemble rebuilding
============================================================
PREDICTION MODES
1. RUN NEXT-DAY MARKET PREDICTION
Purpose: Predict next FCPO trading day direction using completed OHLC historical candles.
Prediction Output:
BUY
SELL
NO TRADE
Analysis Components:
historical market behavior
volatility structure
momentum continuation
market regime analysis
trend continuation probability
ensemble confidence weighting
============================================================
2. RUN TODAY MARKET PREDICTION
Purpose: Predict whether the current FCPO trading day is likely to close bullish or bearish BEFORE market close.
The prediction must use today Open price together with historical FCPO market behavior and live market structure analysis.
============================================================
SAME-DAY AI INPUT ENGINE
For stronger same-day prediction accuracy, the AI engine must analyze:
Today Open Price
Previous Day OHLC
Previous Volatility Structure
Previous Momentum Structure
Current Market Regime
Historical FCPO Market Behavior
Historical Trend Continuation Patterns
AI Ensemble Probability Distribution
Optional Additional Inputs
Intraday Price Movement
Intraday Volatility Expansion
Early Session Momentum Shift
============================================================
SAME-DAY MARKET PREDICTION LOGIC
BUY
Expected Today Close > Today Open
SELL
Expected Today Close < Today Open
Optional: NO TRADE
Triggered when:
intraday structure becomes unstable
AI confidence weakens
volatility becomes abnormal
ensemble signals conflict
============================================================
LIVE MARKET ANALYSIS ENGINE
The system must dynamically evaluate:
bullish vs bearish pressure
trend continuation probability
volatility expansion probability
market structure transition
historical behavioral similarity
AI ensemble confidence
regime transition probability
momentum persistence strength
Prediction confidence must improve dynamically as more market data becomes available during trading hours.
============================================================
AI & MATHEMATICAL ENGINE
The application must initially test ALL mathematical models during historical optimization and backtesting before determining final ensemble weighting.
CORE AI ENGINE
XGBoost
LightGBM
CatBoost
SVM
VOLATILITY ENGINE
GARCH
EGARCH
Heston Model
Stochastic Volatility Model
MARKET STRUCTURE ENGINE
Structural VAR
VECM
Hidden Markov Model (HMM)
TREND FILTER ENGINE
Kalman Filter
DEEP LEARNING ENGINE
LSTM
GRU
SUPPORTING MODELS
Random Forest
Bayesian Network
ARIMA
SARIMA
Monte Carlo Simulation
FINAL AI ENGINE
Stacking Ensemble Model
============================================================
AI SYSTEM DESIGN REQUIREMENTS
The application must NOT remove any mathematical models before full historical backtesting and optimization are completed.
System Requirements
test all models
test all model combinations
compare historical accuracy
compare prediction stability
compare retraining efficiency
compare overfitting risk
compare market adaptability
compare long-term consistency
compare regime sensitivity
compare confidence calibration
Post-Optimization Logic
After optimization:
weaker models may receive lower weighting
unstable models may be disabled
stronger models may receive higher ensemble priority
Primary Objectives
highest realistic prediction accuracy
stable BUY/SELL prediction
adaptive market learning
smooth retraining workflow
fast analysis execution
sustainable long-term stability
minimal overfitting risk
strong confidence calibration
stable live-market prediction performance
============================================================
SMART AUTO-RETRAINING SYSTEM
The application must automatically retrain whenever new Excel candle data is detected.
When new candle data is added:
System Actions
Detect newly added rows automatically
Update:
market structure
volatility regime
trend direction
AI feature layers
historical sequence learning
ensemble confidence
momentum state
market condition classification
Retrain AI models automatically
Reoptimize:
ensemble weighting
feature importance
model confidence
prediction stability
signal reliability
model prioritization
Generate latest prediction automatically
============================================================
USER WORKFLOW
STEP 1
Open Application
STEP 2
Enter License Key
STEP 3
Paste Excel File Directory
STEP 4
Select Training Mode
RUN USING LAST MACHINE LEARNING
RE-RUN MACHINE LEARNING FROM FIRST DATA
STEP 5
Select Prediction Mode
RUN NEXT-DAY MARKET PREDICTION
RUN TODAY MARKET PREDICTION
STEP 6
Click RUN ANALYSIS
STEP 7
Application automatically:
load Excel dataset
validate market data
update AI learning
retrain models
optimize ensemble
generate prediction
display final market signal
============================================================
SYSTEM ARCHITECTURE
Frontend
Command Prompt Interface
Backend
Python AI Engine
Data Source
Excel OHLC Dataset
AI Framework
Hybrid Machine Learning + Statistical Models
Training System
Smart Automatic Retraining Engine
Prediction Output
BUY / SELL / NO TRADE
Deployment
Standalone Windows .EXE Application
============================================================
FINAL DELIVERY REQUIREMENT
The entire application must be fully completed, including:
AI engine development
smart retraining architecture
optimization workflow
historical backtesting engine
Windows .EXE packaging
encrypted license key system
Excel integration
automatic retraining workflow
prediction logging system
user operation manual
Final User Workflow
Download application
Enter license key
Link Excel dataset
Select training mode
Select prediction mode
Run analysis
============================================================