Logistics decision intelligence · Saudi Arabia
Customer windowNetwork point

Optimise the network
around the promise.

Ordinal is a logistics decision intelligence company. Every promise changes the network, so we evaluate the consequence before the commitment is made.

Today that means delivery-window decisioning and network optimisation: customer preferences evaluated against capacity, commitments and constraints. Works alongside your existing logistics stack.

01The approach

Today, someone has to compromise.

Either the operator keeps control of the network and the customer loses timing control, or the customer chooses and the network inherits the consequence.

Model 01
Operator-first delivery
  1. ·Order
  2. ↓Route built
  3. ↓Customer contacted
  4. ↓Delivery when operationally convenient

The operator retains flexibility, but the customer has little control over when the delivery actually arrives.

Model 02
Customer-first scheduling
  1. ·Order
  2. ↓Customer chooses a date / window
  3. ↓Promise becomes fixed
  4. ↓Network absorbs the constraint

The customer gets more choice, but the network inherits commitments before their operational impact is fully understood.

Model 03Third model
Ordinal
  1. ·Order
  2. ↓Network-aware choices
  3. ↓Customer selects
  4. ↓Hard commitment
  5. ↓Optimised fulfilment

Ordinal makes customer choice and network efficiency part of the same decision.

Customer preference and operational efficiency.

02Continuous network state

Every promise changes the network.

Ordinal evaluates new delivery decisions against existing commitments, fleet availability and operational constraints, so each recommendation reflects the network as it stands now, not an isolated shipment.

A customer choosing Tuesday at 11:00 instead of Wednesday at 15:00 can change route density, driver time, capacity utilisation and whether another vehicle is required. Most systems only optimise after that decision has been made.

NETWORK STATE / SEQUENCE OF COMMITMENTSConceptual
  • Commitment 01

    Becomes part of the network state.

  • Commitment 02

    Evaluated against commitment 01.

  • Commitment 03

    Evaluated against everything promised so far.

  • Next decision

    Reflects the network as it stands now.

Optimise the commitment
before optimising the route.

03How Ordinal works

Five stages, one decision.

From operational data to a delivery commitment the network can actually serve, with every commitment shaping what can be promised next.

  1. 01 /
    Understand the network

    Ordinal receives operational demand, fleet and delivery-preference data: orders, delivery coordinates and dates, preferred windows, flexibility levels, parcel volume, service time, drivers, vehicles, capacity, shifts and depots.

    • Orders
    • Delivery coordinates
    • Delivery dates
    • Preferred windows
    • Flexibility levels
    • Parcel volume
    • Service time
    • Drivers and vehicles
    • Vehicle capacity
    • Shifts
    • Depot locations
    • Existing commitments
  2. 02 /
    Model the constraints

    The engine models capacity, shifts, service time, geography, existing commitments and customer preferences together, rather than treating a requested delivery time as an isolated preference.

    • Capacity
    • Shifts
    • Service time
    • Geography
    • Existing commitments
    • Customer preferences
  3. 03 /
    Evaluate the alternatives

    For each eligible date and time window, Ordinal evaluates how the delivery could fit into the current network and whether it is operationally feasible.

    • Incremental distance
    • Incremental driver time
    • Waiting
    • Additional vehicle requirements
    • Time-window feasibility
    • Capacity feasibility
    • Nearby order density
    • Slot capacity pressure
    • Daily network pressure
  4. 04 /
    Recommend

    Ordinal ranks the viable options according to their operational consequences. The customer or operator still chooses. Ordinal changes which choices are operationally attractive, not whether there is a choice.

    Delivery options
    • ★ THU 13:00–15:00Recommended
    • THU 15:00–17:00Feasible
    • FRI 09:00–11:00Feasible
  5. 05 /
    Commit

    Once a delivery window is selected, the commitment becomes part of the network state considered by subsequent decisions. The committed network is then solved as a full routing problem with time windows.

    • Date + window
    • Hard operational commitment
    Committed orders
    ↓
    VRPTW optimisation
    ↓
    Routes and dispatch
Preference and constraint levels
Flexible

The delivery can move when doing so materially improves the network.

Preferred

The requested window is prioritised, but alternatives may be considered when operationally beneficial.

Hard

The specified delivery constraint must be respected.

Each level is evaluated against operational feasibility and network consequences, not applied as a fixed rule.

Estimate before choice.
Optimise after commitment.

04Control versus Ordinal

Same orders. Same fleet.
Different decision logic.

Both worlds face the same demand, the same geography, the same fleet and the same fulfilment solver. Only the way delivery commitments are formed differs.

Control
  • ·Same orders
  • ·Same geography
  • ·Same fleet
  • ·Same delivery-choice universe
  • ·No network-aware recommendation
Customer commitments
↓
Routing
↓
Compare
Ordinal
  • ·Same orders
  • ·Same geography
  • ·Same fleet
  • ·Same fulfilment solver
  • ·Delivery options evaluated against network impact
Customer commitments
↓
Routing
↓
Compare
Metrics compared
  • Kilometres
  • Driver-hours
  • Routes
  • Vehicle-days
  • Vehicles used
  • Orders served
  • Unassigned orders
Same orders · same fleet · control commitments
Network
112 delivery points
Fleet
  • DRIVER 01
  • DRIVER 02
  • DRIVER 03
  • DRIVER 04

Commitments were formed without network context. Routes absorb the consequence.

Same orders. Same fleet.
Different constraints. Different routes.

05Marginal network impact

What does one more delivery do to the network?

Ordinal does not recommend the emptiest delivery slot. An empty slot can be expensive if serving it creates an isolated trip, additional waiting or another vehicle.

Where can this order enter the network at the lowest marginal operational cost?

NEW ORDER / 24.7550, 46.7200Illustrative example
    Option AFeasible
    Thu / 09:00–11:00
    Distance
    +8.4 km
    Driver time
    +31 min
    Fleet
    +1 vehicle
    Option BRecommended
    Thu / 13:00–15:00
    Distance
    +1.2 km
    Driver time
    +7 min
    Fleet
    +0 vehicles
    Option CFeasible
    Fri / 09:00–11:00
    Distance
    +14.1 km
    Driver time
    +68 min
    Fleet
    +1 vehicle
Recommend → Option BNot measured performance

Illustrative example. Figures are shown to explain the evaluation, not to claim savings.

06Two ways operators use Ordinal

Model the opportunity. Then decide in operation.

One workflow studies a network from supplied data. The other evaluates individual delivery-window decisions against the live network state.

AWorkflow
Analyse your network

Ordinal analyses historical or supplied network data and compares your current delivery network against an Ordinal-optimised scenario. Analyses run independently in the background and the results remain available once complete.

What could change if customer delivery preferences were part of network planning?

  • Distance
  • Driver hours
  • Route utilisation
  • Vehicle-days
  • Orders served
  • Unassigned orders
  • Delivery-window performance
  • Fleet utilisation
BWorkflow
Live delivery-window decisioning

When a shipment needs a delivery-window decision, the engine evaluates feasible alternatives against the network as it currently stands and returns ranked delivery-window options.

Which delivery windows can this network honour without adding avoidable cost?

  • Available fleet
  • Vehicle capacity
  • Driver shifts
  • Existing commitments
  • Delivery date
  • Window constraints
  • Parcel volume
  • Service time
  • Incremental distance
  • Incremental driver time
  • Routing implications
  • Operational feasibility
LIVE DECISION / SEQUENCEConceptual
  1. 01
    Shipment
  2. 02
    Operational context
  3. 03
    Feasibility evaluation
  4. 04
    Candidate windows
  5. 05
    Ranked recommendation
  6. 06
    Selection
  7. 07
    Delivery commitment

Ordinal recommends and records delivery commitments. It does not dispatch vehicles and does not replace a transport management system.

08Why Ordinal

Not another route planner.
Decision intelligence.

Routing answers how to serve the orders you already accepted. Ordinal helps decide which delivery promises should enter the network at all.

01
Customer preference

Logistics decisions should account for when customers actually want their orders, not only how to move them efficiently.

02
Network-aware decisions

A delivery promise is evaluated against the wider network before it is offered.

03
Operational feasibility

Recommendations account for real constraints: capacity, shifts, service time and existing commitments.

04
Incremental impact

Ordinal evaluates what adding or changing a commitment does to the network.

05
Works alongside existing operations

A decision intelligence layer, not a forced replacement for your logistics stack.

06
Saudi-first

Built around the realities of Saudi delivery operations: growing volumes, dense urban networks and rising customer expectations.

09 / Maturity

Production infrastructure.
Pilot-stage deployment.

Ordinal is built for controlled pilot deployments. We are now working with operators on network analysis and pilot opportunities.

Persistent network state

Delivery commitments and network state persist across analyses and operational decisions.

Background analysis

Network analyses run independently in the background and remain available when complete.

Isolated environments

Customer operational environments are logically isolated from one another.

Operated infrastructure

A secured production API with monitoring, backup and recovery mechanisms in place.

06 / Customer experience

A delivery window should be a promise.

Some delivery models provide almost no timing control to the recipient. Others ask customers to select a delivery window but struggle to consistently fulfil those preferences once the route is built. Ordinal's architecture is designed to make the promise operationally informed before it is offered.

Without Ordinal

"We'll contact you when the driver is nearby."

↓
Network tries to accommodate it later.

With Ordinal

"Choose from delivery options that already fit the network."

↓
Selection becomes a commitment.
↓
Network is optimised around it.

Choice that the network
can actually support.

07Counterfactual validation

Does Ordinal actually cause the improvement?

Each simulated customer has an underlying uninfluenced delivery choice. In Control, the customer selects that choice. In Ordinal, the customer either follows the recommendation or makes the same uninfluenced choice they would have made in Control.

At 0% influence, Control and Ordinal should converge. As influence increases, a genuine mechanism should strengthen the network effect.

RECOMMENDATION INFLUENCE / MEAN DISTANCE EFFECTDevelopment simulation · synthetic demand
  • 0%0%
  • 20%11.1%
  • 40%15.1%
  • 60%23.3%
  • 80%39.6%
  • 100%52.0%

These results demonstrate the behaviour of the current model under controlled synthetic conditions. They are not claims of expected savings in live commercial operations.

09Where Ordinal sits

A decision layer between commerce and fulfilment.

Ordinal is designed to complement an operator's existing logistics stack rather than replace it.

Its primary role is upstream of routing: helping determine which delivery promises should enter the network in the first place.

DECISION LAYER / POSITIONUpstream of routing
Ecommerce / OMS / order source
↓
New order
↓
Ordinal
  • Read network
  • Evaluate options
  • Recommend
  • Capture commitment
↓
Delivery commitment
↓
TMS / routing / dispatch
↓
Fulfilment
10The commercial journey

Prove it before you deploy it.

Ordinal starts with your historical network, not a software implementation.

01
Analyse your network
Free

See what Ordinal could do to your network.

Provide anonymised historical delivery data. We reconstruct the network, replay it with network-aware delivery options and compare the result against the control world.

Analyse Your Network →
  • ·Historical data
  • ·Control replay
  • ·Ordinal replay
  • ·Comparison report
↓
02
Pilot
Discounted

Put the model into operation.

Once the analysis shows a meaningful opportunity, run Ordinal against a defined network or operating period at a discounted pilot rate, starting in shadow mode where appropriate.

Pilot pricing is designed to reduce the barrier to proving operational value.

Discuss a Pilot →
  • ·Defined network
  • ·Agreed KPIs
  • ·Operational testing
  • ·Performance validation
↓
03
Annual
Full commercial

Make optimisation part of the operation.

After the pilot validates the economics and operational performance, move to an annual Ordinal contract.

  • ·Ongoing optimisation
  • ·Operational use
  • ·Performance monitoring
  • ·Network expansion
Analyse your network

We show you the opportunity.

Pilot

We prove it in operation.

Annual

We make it part of the operation.

First we analyse. Then we prove. Then we deploy.

11Analyse your network, free

Start with your network.
Not an integration.

Give us a sample of your historical delivery data. We reconstruct the network, replay it under control and Ordinal decision logic, and return a clear comparison.

ANALYSE YOUR NETWORK / SEQUENCEIllustrative
01
Your data
↓
02
Control replay
↓
03
Ordinal replay
↓
04
Comparison
↓
05
Network report
Output
Report categories
  • Kilometres
  • Driver-hours
  • Vehicle utilisation
  • Routes
  • Vehicle-days
  • Unassigned orders

Illustrative categories. Figures are produced from your own network, never invented.

Analyse Your Network →One-off analysis and report. No checkout integration, no deployment, no change to your operation.
12What Ordinal needs

Start with what you have.

The exact dataset can be discussed with Ordinal before an analysis begins. We work with the operational data you already hold, anonymised where you prefer.

Orders
  • ·Shipment or order identifier
  • ·Delivery location
  • ·Delivery date
  • ·Preferred delivery window, where available
  • ·Parcel size or volume
  • ·Estimated service time
Fleet
  • ·Driver or vehicle identifier
  • ·Vehicle capacity
  • ·Shift availability
  • ·Depot location
Helpful, not required
  • ·Historical routes
  • ·Actual delivery times
  • ·Failed delivery events
No integration

No integration.
No disruption.

Before integration,
there is analysis.

Supplied operational data
is enough to start.

Ordinal works alongside your existing logistics stack. A later production deployment may still involve technical work, agreed with you in advance.

13Who it is for

Built for delivery networks where the promise and the network cannot be decided separately.

Operators managing time-window commitments across a shared fleet.

  • 01Last-mile delivery networksHigh order density, tight time-window commitments.
  • 02Retail delivery operationsStore and warehouse fulfilment with promised slots.
  • 03E-commerce fulfilment networksDelivery promises made before the route exists.
  • 04Fleet operatorsOwned or contracted capacity planned day by day.
14Pilot

Start with your network.

Ordinal does not need to be deployed into checkout on day one. The first step is to evaluate the system against historical delivery operations.

Analyse Your Network →

No checkout integration is required for the initial analysis.

01 /
Provide data
  • ·Order coordinates
  • ·Delivery dates / windows
  • ·Depot locations
  • ·Vehicle capacities
  • ·Driver shifts
  • ·Service times
  • ·Historical routes where available
02 /
Replay
  • ·Reconstruct the historical network
  • ·Evaluate how Ordinal would have shaped delivery commitments
  • ·Explicit customer-response assumptions
03 /
Compare
  • ·Kilometres
  • ·Driver-hours
  • ·Vehicle utilisation
  • ·Routes
  • ·Feasibility
  • ·Estimated operating impact
15Annual

From experiment to infrastructure.

When the pilot proves the operational and economic case, Ordinal moves from an experiment into the operator's ongoing optimisation process.

  • ·Additional depots
  • ·Additional regions
  • ·Additional delivery volume
  • ·Additional optimisation use cases

Annual agreements are scoped to the network they cover.

16FAQ
  • Yes. The first stage is a one-off analysis and report at no cost. It does not include access to the Ordinal system; that begins with a pilot.

  • Orders with delivery locations, dates, preferred windows where they exist, parcel volume and service time, plus fleet details: vehicles, capacity, shifts and depots. Anonymised is fine, and the exact dataset is agreed before we begin.

  • Not to start. The initial analysis runs on supplied operational data with no connection to your production systems. A later live deployment is scoped with you.

  • No. Ordinal sits ahead of them, deciding which delivery windows are worth offering. It does not dispatch vehicles. Existing planning and execution systems stay in place.

  • Ordinal estimates the marginal operational impact of each eligible date and window against the current network: incremental distance, driver time, vehicle requirements, capacity and feasibility. The full routing problem is solved after commitment, not for every option shown.

  • Delivery preferences are modelled at three levels. Flexible deliveries can move when it materially improves the network, preferred windows are prioritised, and hard constraints must be respected.

  • Ordinal runs on production infrastructure with persistent network state, background analysis and a secured API. Commercially it remains in controlled pilot and early deployment.

  • No. The current figures come from a development simulation on synthetic demand under a counterfactual design. They show how the mechanism behaves, not expected commercial savings.

  • Days, not quarters, once the data is available.

Free network analysis

Request a free network analysis.

Give Ordinal a representative historical delivery set. See what changes when delivery demand becomes a decision variable.

Analyse Your Network →

Historical data only. No checkout integration required for the initial analysis.