SIH26006: Development of an Intelligent Freight Forecasting Model for Optimized Vessel Cha — SIH 2026 | Wynit

SIH26006: Development of an Intelligent Freight Forecasting Model for Optimized Vessel Cha — SIH 2026 | Wynit

What they'll ask you

14

Generated from the brief's own wording and the competition's published rules, never from a guess about what this ministry prefers.

Specific source or API access for real-time freight rates and port congestion data?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Target prediction accuracy percentage or error threshold?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Minimum historical time period required for model training?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.

11 morethe ones a panel gets to if there is time

Has any part of this been shown at a previous event, hackathon or college project?
The guidelines are explicit: your solution must not have appeared in any previous event or programme, of any sort. A recycled project is what a team under time pressure reaches for.
The brief asks for freight forecasting engine. How would you build that?
Decoded from SIH26006 itself: Uses time series and regression models to predict future freight rates across specific shipping routes and vessel classes. The brief asks for it by name.
The brief asks for port infrastructure matcher. How would you build that?
Decoded from SIH26006 itself: Filters eligible vessel sizes by checking cargo volume against physical port constraints like draft, length overall, and handling speeds. The brief asks for it by name.
The brief asks for charter timing optimizer. How would you build that?
Decoded from SIH26006 itself: Analyzes market trends to recommend the best time window for signing short-term or medium-term charter contracts. The brief asks for it by name.
The brief asks for risk and congestion monitor. How would you build that?
Decoded from SIH26006 itself: Tracks port congestion and market volatility to issue early warning alerts to supply chain managers. The brief asks for it by name.
The brief asks for logistics decision portal. How would you build that?
Decoded from SIH26006 itself: A web dashboard where users enter cargo details and port pairs to generate cost predictions and routing recommendations. The brief asks for it by name.
Where does your data come from: a published source, one you collect, or one you generate?
No dataset is attached to this problem statement, so sourcing it is part of the work and nobody told you that.
Why not use what already exists? Name the closest thing to this that is already running.
A team that has not named the alternative themselves is answering this for the first time in the room.
Which single thing will you demonstrate end to end, start to finish, with nothing skipped?
Ours, not a rule: a narrow thing that fully works survives questioning better than a broad thing that half works. If nobody on the team can name it, that is the finding.
Show me this working: evaluators will check if the model accounts for explicit port constraints like draft, beam, length overall, and handling rates at specified East Coast Indian ports.
This is the evaluator read for your problem statement, decoded from the brief's own wording.
Show me this working: they will assess whether the solution provides actionable entry timing recommendations instead of just raw price charts.
This is the evaluator read for your problem statement, decoded from the brief's own wording.

The government's original description (677 words)

Background: The current approach to vessel chartering for bulk cargo procurement to India's East Coast ports often involves daily market exploration, leading to reactive decision-making and likely missed opportunities for cost savings and efficiency. The highly volatile nature of global freight markets, coupled with varying supply and demand dynamics from key origins like Australia, the US, Mozambique, Russia and Indonesia, makes it challenging to identify optimal entry points for short-term or mid-term charter contracts. Furthermore, without a robust future forecasting mechanism, determining the most suitable vessel type (e.g., Handysize, Supramax, Panamax,Capesize) for specific cargo parcels and routes, while accounting for port infrastructure limitations at both origin and destination, results in suboptimal utilization and increased idle time. This manual, market-dependent approach requires analytics to mitigate risks associated with freight fluctuations and port-specific constraints, directly impacting overall logistics costs and supply chain reliability. Detailed Description: The problem statement addresses the critical need for a sophisticated freight forecasting model to revolutionize vessel chartering and bulk cargo procurement for East Coast Indian ports. Currently, our operations are heavily reliant on daily engagements with the freight market. This traditional method leads to several inefficiencies: a lack of predictive insight into future freight rates, making it difficult to secure favorable short-term or mid-term charter contracts; an inability to proactively identify the optimal time to enter the market for specific vessel types and cargo sizes; and significant challenges in minimizing vessel idle time due to inadequate planning regarding port-specific infrastructure restrictions. For instance, procuring bulk cargo (such as coal) from Australia, the US,Mozambique, and Indonesia presents unique logistical challenges. Each origin-destination pair has distinct sailing distances, trade lane dynamics, and, crucially,varying port capabilities. East Coast Indian ports, like Paradip, Vizag, Gangavaram,Gopalpur, Dhamra, Sagar- Sandheads and Haldia, each possess specific draft restrictions, berthing limitations, and cargo handling capacities that dictate the maximum permissible vessel size and turnaround time.The proposed system should therefore integrate multiple data points for comprehensive analysis. This includes historical freight rate data for various vessel sizes across relevant trade routes, global economic indicators, commodity price trends, seasonal variations in demand and supply, and real-time port congestion information for both origin and destination ports. Furthermore, it must incorporate detailed infrastructure constraints of Indian East Coast ports, such as maximum LOA (Length Overall), beam, draft, and cargo handling rates, along with similar data for the loading ports in Australia, the US, Mozambique, and Indonesia. Expected Solution: The expected solution is the development and implementation of an intelligent, datadriven Freight Forecasting Model. This model should leverage advanced analytical techniques, potentially including machine learning algorithms (e.g., time series forecasting, regression models) and artificial intelligence, to predict future freight rates with a high degree of accuracy for various vessel types and trade routes. The solution should offer actionable insights by providing recommendations on: a. Optimal Market Entry Timing: Identify ideal windows to secure short-term or mid-term vessel charter contracts for specific cargo requirements, minimizing freight costs. b. Vessel Type Optimization: Recommend the most suitable vessel type (e.g.,Handysize, Supramax, Panamax, Capesize) for a given cargo volume and origin-destination pair, considering all known port infrastructure limitations at both loading and discharge ports on India's East Coast. This includes factoring in draft restrictions, LOA, and cargo handling capabilities to prevent idle time and ensure efficient turnaround. c. Idle Scenario Management: Propose strategies for minimizing vessel idle time by forecasting periods of low demand and suggesting alternative employment opportunities or optimized positioning to reduce deadheading. d. Risk Mitigation: Provide early warnings for potential market volatility, port congestion, or other disruptions that could impact chartering decisions. The model should be user-friendly, perhaps with a dashboard interface, allowing logistics managers to input cargo details, origin/destination ports, and desired contract duration to receive comprehensive freight forecasts and actionable recommendations.The ultimate goal is to move from a reactive, daily market approach to a proactive, predictive chartering strategy, leading to significant cost reductions, improved supply chain efficiency, and enhanced decision-making capabilities. Objective: Development of model to facilitate moving from multiple single spot contracts being entered into currently to short term / medium term multiple voyage contracts.